Epoch: 0001 train_loss= 0.82333 train_acc= 0.48312 val_loss= 0.80272 val_acc= 0.34426 time= 0.28419
Epoch: 0002 train_loss= 0.96894 train_acc= 0.48442 val_loss= 0.82064 val_acc= 0.40984 time= 0.00410
Epoch: 0003 train_loss= 1.20994 train_acc= 0.46883 val_loss= 0.89231 val_acc= 0.49180 time= 0.01563
Epoch: 0004 train_loss= 0.90491 train_acc= 0.49740 val_loss= 1.17501 val_acc= 0.47541 time= 0.01563
Epoch: 0005 train_loss= 0.99802 train_acc= 0.52987 val_loss= 1.59429 val_acc= 0.47541 time= 0.01563
Epoch: 0006 train_loss= 1.14700 train_acc= 0.51948 val_loss= 1.76494 val_acc= 0.47541 time= 0.01563
Epoch: 0007 train_loss= 2.70044 train_acc= 0.52857 val_loss= 1.68334 val_acc= 0.47541 time= 0.00000
Epoch: 0008 train_loss= 0.89865 train_acc= 0.52468 val_loss= 1.63157 val_acc= 0.47541 time= 0.01563
Epoch: 0009 train_loss= 1.72140 train_acc= 0.53506 val_loss= 1.43448 val_acc= 0.47541 time= 0.01563
Epoch: 0010 train_loss= 1.03985 train_acc= 0.52597 val_loss= 1.24140 val_acc= 0.47541 time= 0.01563
Epoch: 0011 train_loss= 1.45292 train_acc= 0.48961 val_loss= 1.15405 val_acc= 0.47541 time= 0.01563
Epoch: 0012 train_loss= 1.00027 train_acc= 0.54156 val_loss= 1.05720 val_acc= 0.45902 time= 0.01563
Epoch: 0013 train_loss= 1.48994 train_acc= 0.52468 val_loss= 0.94215 val_acc= 0.45902 time= 0.00000
Epoch: 0014 train_loss= 1.68894 train_acc= 0.52338 val_loss= 0.81808 val_acc= 0.47541 time= 0.01563
Epoch: 0015 train_loss= 1.18643 train_acc= 0.48442 val_loss= 0.76920 val_acc= 0.47541 time= 0.01563
Epoch: 0016 train_loss= 0.97312 train_acc= 0.51299 val_loss= 0.73869 val_acc= 0.44262 time= 0.01563
Epoch: 0017 train_loss= 1.48324 train_acc= 0.47532 val_loss= 0.73592 val_acc= 0.45902 time= 0.01562
Epoch: 0018 train_loss= 1.29401 train_acc= 0.53636 val_loss= 0.73498 val_acc= 0.44262 time= 0.01563
Epoch: 0019 train_loss= 0.79974 train_acc= 0.45974 val_loss= 0.74195 val_acc= 0.37705 time= 0.00000
Epoch: 0020 train_loss= 1.83347 train_acc= 0.48701 val_loss= 0.73410 val_acc= 0.42623 time= 0.01563
Epoch: 0021 train_loss= 0.86947 train_acc= 0.51169 val_loss= 0.73061 val_acc= 0.49180 time= 0.01563
Epoch: 0022 train_loss= 1.68898 train_acc= 0.48052 val_loss= 0.74439 val_acc= 0.42623 time= 0.01563
Epoch: 0023 train_loss= 1.01173 train_acc= 0.51558 val_loss= 0.76364 val_acc= 0.47541 time= 0.01563
Epoch: 0024 train_loss= 1.13105 train_acc= 0.47662 val_loss= 0.77703 val_acc= 0.45902 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.83765 accuracy= 0.49180 time= 0.01563 
