Epoch: 0001 train_loss= 1.81382 train_acc= 0.49221 val_loss= 1.53986 val_acc= 0.47541 time= 0.71333
Epoch: 0002 train_loss= 2.28939 train_acc= 0.49740 val_loss= 1.27464 val_acc= 0.47541 time= 0.01300
Epoch: 0003 train_loss= 2.06482 train_acc= 0.50130 val_loss= 1.17677 val_acc= 0.44262 time= 0.01300
Epoch: 0004 train_loss= 1.20235 train_acc= 0.49481 val_loss= 1.24914 val_acc= 0.49180 time= 0.01300
Epoch: 0005 train_loss= 1.53208 train_acc= 0.53896 val_loss= 1.33435 val_acc= 0.49180 time= 0.00298
Epoch: 0006 train_loss= 1.13376 train_acc= 0.50000 val_loss= 1.35800 val_acc= 0.45902 time= 0.01562
Epoch: 0007 train_loss= 1.30882 train_acc= 0.50909 val_loss= 1.40170 val_acc= 0.49180 time= 0.01563
Epoch: 0008 train_loss= 1.23399 train_acc= 0.50779 val_loss= 1.36240 val_acc= 0.49180 time= 0.01563
Epoch: 0009 train_loss= 1.00884 train_acc= 0.50390 val_loss= 1.30197 val_acc= 0.49180 time= 0.00000
Epoch: 0010 train_loss= 0.95783 train_acc= 0.48961 val_loss= 1.22417 val_acc= 0.50820 time= 0.01563
Epoch: 0011 train_loss= 1.38411 train_acc= 0.47532 val_loss= 1.13839 val_acc= 0.54098 time= 0.01563
Epoch: 0012 train_loss= 1.07399 train_acc= 0.51039 val_loss= 1.06515 val_acc= 0.57377 time= 0.01563
Epoch: 0013 train_loss= 0.88497 train_acc= 0.49351 val_loss= 1.00282 val_acc= 0.49180 time= 0.01563
Epoch: 0014 train_loss= 0.84961 train_acc= 0.49351 val_loss= 0.94641 val_acc= 0.49180 time= 0.01563
Epoch: 0015 train_loss= 0.91086 train_acc= 0.50519 val_loss= 0.89860 val_acc= 0.50820 time= 0.00000
Epoch: 0016 train_loss= 0.83295 train_acc= 0.51818 val_loss= 0.85987 val_acc= 0.50820 time= 0.01563
Epoch: 0017 train_loss= 0.83143 train_acc= 0.50260 val_loss= 0.83005 val_acc= 0.47541 time= 0.01562
Epoch: 0018 train_loss= 1.02464 train_acc= 0.50649 val_loss= 0.81344 val_acc= 0.45902 time= 0.01563
Epoch: 0019 train_loss= 1.07158 train_acc= 0.47013 val_loss= 0.80095 val_acc= 0.45902 time= 0.01930
Epoch: 0020 train_loss= 0.95563 train_acc= 0.47273 val_loss= 0.79263 val_acc= 0.47541 time= 0.01202
Epoch: 0021 train_loss= 1.18698 train_acc= 0.48052 val_loss= 0.78694 val_acc= 0.47541 time= 0.00000
Epoch: 0022 train_loss= 0.74613 train_acc= 0.50779 val_loss= 0.78100 val_acc= 0.47541 time= 0.01563
Epoch: 0023 train_loss= 1.21876 train_acc= 0.50130 val_loss= 0.77983 val_acc= 0.49180 time= 0.01563
Epoch: 0024 train_loss= 0.89691 train_acc= 0.48571 val_loss= 0.78084 val_acc= 0.49180 time= 0.01563
Epoch: 0025 train_loss= 1.05707 train_acc= 0.50519 val_loss= 0.78431 val_acc= 0.52459 time= 0.01563
Epoch: 0026 train_loss= 0.87890 train_acc= 0.48442 val_loss= 0.79078 val_acc= 0.49180 time= 0.00000
Epoch: 0027 train_loss= 0.80276 train_acc= 0.50519 val_loss= 0.79731 val_acc= 0.49180 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.78734 accuracy= 0.45082 time= 0.01563 
