Epoch: 0001 train_loss= 1.21830 train_acc= 0.46182 val_loss= 0.68644 val_acc= 0.54098 time= 0.57816
Epoch: 0002 train_loss= 0.78344 train_acc= 0.48727 val_loss= 0.70336 val_acc= 0.55738 time= 0.03125
Epoch: 0003 train_loss= 0.74575 train_acc= 0.51273 val_loss= 0.73548 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 0.72114 train_acc= 0.48364 val_loss= 0.76155 val_acc= 0.52459 time= 0.01563
Epoch: 0005 train_loss= 0.71142 train_acc= 0.49818 val_loss= 0.77034 val_acc= 0.52459 time= 0.03383
Epoch: 0006 train_loss= 0.73007 train_acc= 0.46545 val_loss= 0.76278 val_acc= 0.52459 time= 0.02100
Epoch: 0007 train_loss= 0.70595 train_acc= 0.47091 val_loss= 0.77074 val_acc= 0.52459 time= 0.02301
Epoch: 0008 train_loss= 0.82190 train_acc= 0.52364 val_loss= 0.75678 val_acc= 0.54098 time= 0.02000
Epoch: 0009 train_loss= 0.74966 train_acc= 0.52909 val_loss= 0.74123 val_acc= 0.54098 time= 0.02100
Epoch: 0010 train_loss= 0.72031 train_acc= 0.49091 val_loss= 0.72310 val_acc= 0.54098 time= 0.02300
Epoch: 0011 train_loss= 0.71214 train_acc= 0.53455 val_loss= 0.70415 val_acc= 0.54098 time= 0.02301
Epoch: 0012 train_loss= 0.74068 train_acc= 0.50364 val_loss= 0.68624 val_acc= 0.54098 time= 0.02200
Epoch: 0013 train_loss= 0.70457 train_acc= 0.52364 val_loss= 0.67982 val_acc= 0.55738 time= 0.02200
Epoch: 0014 train_loss= 0.71393 train_acc= 0.51455 val_loss= 0.67653 val_acc= 0.55738 time= 0.02100
Epoch: 0015 train_loss= 0.72534 train_acc= 0.50364 val_loss= 0.67524 val_acc= 0.54098 time= 0.02100
Epoch: 0016 train_loss= 0.69512 train_acc= 0.50364 val_loss= 0.67580 val_acc= 0.52459 time= 0.02000
Epoch: 0017 train_loss= 0.69379 train_acc= 0.53636 val_loss= 0.67640 val_acc= 0.54098 time= 0.02201
Epoch: 0018 train_loss= 0.70508 train_acc= 0.51091 val_loss= 0.67674 val_acc= 0.59016 time= 0.02000
Epoch: 0019 train_loss= 0.69831 train_acc= 0.52182 val_loss= 0.67708 val_acc= 0.59016 time= 0.02401
Epoch: 0020 train_loss= 0.71246 train_acc= 0.51091 val_loss= 0.67726 val_acc= 0.59016 time= 0.02201
Epoch: 0021 train_loss= 0.69358 train_acc= 0.50727 val_loss= 0.67726 val_acc= 0.60656 time= 0.02201
Epoch: 0022 train_loss= 0.69495 train_acc= 0.49818 val_loss= 0.67711 val_acc= 0.60656 time= 0.02000
Epoch: 0023 train_loss= 0.69158 train_acc= 0.50545 val_loss= 0.67694 val_acc= 0.59016 time= 0.02000
Early stopping...
Optimization Finished!
Test set results: cost= 0.70148 accuracy= 0.53279 time= 0.00900 
