Epoch: 0001 train_loss= 1.01076 train_acc= 0.51299 val_loss= 0.70256 val_acc= 0.55738 time= 0.31831
Epoch: 0002 train_loss= 1.00914 train_acc= 0.48831 val_loss= 0.68948 val_acc= 0.57377 time= 0.01300
Epoch: 0003 train_loss= 0.97024 train_acc= 0.50649 val_loss= 0.70293 val_acc= 0.60656 time= 0.01300
Epoch: 0004 train_loss= 0.88703 train_acc= 0.51429 val_loss= 0.74928 val_acc= 0.62295 time= 0.01300
Epoch: 0005 train_loss= 0.84075 train_acc= 0.51299 val_loss= 0.76007 val_acc= 0.62295 time= 0.01400
Epoch: 0006 train_loss= 1.05020 train_acc= 0.54416 val_loss= 0.73037 val_acc= 0.62295 time= 0.01300
Epoch: 0007 train_loss= 0.86027 train_acc= 0.51039 val_loss= 0.69472 val_acc= 0.59016 time= 0.01200
Epoch: 0008 train_loss= 0.85828 train_acc= 0.54026 val_loss= 0.67956 val_acc= 0.59016 time= 0.01400
Epoch: 0009 train_loss= 0.80513 train_acc= 0.50260 val_loss= 0.67138 val_acc= 0.60656 time= 0.01400
Epoch: 0010 train_loss= 0.78739 train_acc= 0.52078 val_loss= 0.66468 val_acc= 0.62295 time= 0.01200
Epoch: 0011 train_loss= 0.82684 train_acc= 0.53506 val_loss= 0.66885 val_acc= 0.65574 time= 0.01400
Epoch: 0012 train_loss= 0.82809 train_acc= 0.49351 val_loss= 0.67681 val_acc= 0.63934 time= 0.01300
Epoch: 0013 train_loss= 0.92384 train_acc= 0.50130 val_loss= 0.67844 val_acc= 0.62295 time= 0.01500
Epoch: 0014 train_loss= 0.85264 train_acc= 0.47922 val_loss= 0.67657 val_acc= 0.63934 time= 0.01300
Epoch: 0015 train_loss= 0.75459 train_acc= 0.50909 val_loss= 0.67552 val_acc= 0.67213 time= 0.01400
Epoch: 0016 train_loss= 0.76499 train_acc= 0.50260 val_loss= 0.67527 val_acc= 0.65574 time= 0.01300
Epoch: 0017 train_loss= 0.74498 train_acc= 0.51299 val_loss= 0.67751 val_acc= 0.63934 time= 0.01300
Early stopping...
Optimization Finished!
Test set results: cost= 0.76651 accuracy= 0.55738 time= 0.00600 
