Epoch: 0001 train_loss= 0.93983 train_acc= 0.50779 val_loss= 0.76734 val_acc= 0.36066 time= 0.31252
Epoch: 0002 train_loss= 0.97421 train_acc= 0.50649 val_loss= 1.01756 val_acc= 0.37705 time= 0.01563
Epoch: 0003 train_loss= 1.07675 train_acc= 0.51688 val_loss= 1.08956 val_acc= 0.37705 time= 0.01563
Epoch: 0004 train_loss= 0.91295 train_acc= 0.47792 val_loss= 1.10933 val_acc= 0.39344 time= 0.01563
Epoch: 0005 train_loss= 1.60037 train_acc= 0.50519 val_loss= 0.99799 val_acc= 0.36066 time= 0.01563
Epoch: 0006 train_loss= 0.98466 train_acc= 0.48571 val_loss= 0.87058 val_acc= 0.37705 time= 0.01563
Epoch: 0007 train_loss= 0.90136 train_acc= 0.52857 val_loss= 0.77420 val_acc= 0.36066 time= 0.00000
Epoch: 0008 train_loss= 0.89575 train_acc= 0.51429 val_loss= 0.71089 val_acc= 0.47541 time= 0.01563
Epoch: 0009 train_loss= 0.90955 train_acc= 0.53636 val_loss= 0.69449 val_acc= 0.57377 time= 0.01562
Epoch: 0010 train_loss= 0.81453 train_acc= 0.49221 val_loss= 0.69788 val_acc= 0.60656 time= 0.01563
Epoch: 0011 train_loss= 0.89319 train_acc= 0.50390 val_loss= 0.70099 val_acc= 0.62295 time= 0.01563
Epoch: 0012 train_loss= 1.19791 train_acc= 0.50390 val_loss= 0.69286 val_acc= 0.60656 time= 0.01562
Epoch: 0013 train_loss= 0.97121 train_acc= 0.49091 val_loss= 0.68451 val_acc= 0.60656 time= 0.01563
Epoch: 0014 train_loss= 0.78531 train_acc= 0.49870 val_loss= 0.68213 val_acc= 0.59016 time= 0.01563
Epoch: 0015 train_loss= 0.86586 train_acc= 0.47792 val_loss= 0.68570 val_acc= 0.57377 time= 0.01563
Epoch: 0016 train_loss= 0.84695 train_acc= 0.51299 val_loss= 0.69808 val_acc= 0.54098 time= 0.01563
Epoch: 0017 train_loss= 1.02287 train_acc= 0.48442 val_loss= 0.73372 val_acc= 0.39344 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.77118 accuracy= 0.55738 time= 0.00000 
