Epoch: 0001 train_loss= 0.70073 train_acc= 0.46234 val_loss= 0.69981 val_acc= 0.44262 time= 0.67647
Epoch: 0002 train_loss= 0.69887 train_acc= 0.50909 val_loss= 0.70255 val_acc= 0.44262 time= 0.01400
Epoch: 0003 train_loss= 0.69814 train_acc= 0.53247 val_loss= 0.70468 val_acc= 0.44262 time= 0.01300
Epoch: 0004 train_loss= 0.69713 train_acc= 0.52857 val_loss= 0.70668 val_acc= 0.44262 time= 0.01300
Epoch: 0005 train_loss= 0.69718 train_acc= 0.52727 val_loss= 0.70753 val_acc= 0.44262 time= 0.01200
Epoch: 0006 train_loss= 0.69612 train_acc= 0.52857 val_loss= 0.70822 val_acc= 0.44262 time= 0.01300
Epoch: 0007 train_loss= 0.69596 train_acc= 0.52857 val_loss= 0.70857 val_acc= 0.44262 time= 0.01200
Epoch: 0008 train_loss= 0.69620 train_acc= 0.52857 val_loss= 0.70847 val_acc= 0.44262 time= 0.01300
Epoch: 0009 train_loss= 0.69533 train_acc= 0.52857 val_loss= 0.70818 val_acc= 0.44262 time= 0.01300
Epoch: 0010 train_loss= 0.69525 train_acc= 0.52857 val_loss= 0.70766 val_acc= 0.44262 time= 0.01300
Epoch: 0011 train_loss= 0.69473 train_acc= 0.52727 val_loss= 0.70709 val_acc= 0.44262 time= 0.01400
Epoch: 0012 train_loss= 0.69425 train_acc= 0.52857 val_loss= 0.70649 val_acc= 0.44262 time= 0.01300
Epoch: 0013 train_loss= 0.69401 train_acc= 0.52857 val_loss= 0.70594 val_acc= 0.44262 time= 0.01300
Epoch: 0014 train_loss= 0.69424 train_acc= 0.52857 val_loss= 0.70533 val_acc= 0.44262 time= 0.01300
Epoch: 0015 train_loss= 0.69393 train_acc= 0.52857 val_loss= 0.70468 val_acc= 0.44262 time= 0.01200
Epoch: 0016 train_loss= 0.69380 train_acc= 0.52857 val_loss= 0.70410 val_acc= 0.44262 time= 0.01400
Epoch: 0017 train_loss= 0.69315 train_acc= 0.52857 val_loss= 0.70374 val_acc= 0.44262 time= 0.01400
Epoch: 0018 train_loss= 0.69359 train_acc= 0.52857 val_loss= 0.70336 val_acc= 0.44262 time= 0.01200
Epoch: 0019 train_loss= 0.69359 train_acc= 0.52857 val_loss= 0.70297 val_acc= 0.44262 time= 0.01300
Epoch: 0020 train_loss= 0.69302 train_acc= 0.52857 val_loss= 0.70272 val_acc= 0.44262 time= 0.01200
Epoch: 0021 train_loss= 0.69288 train_acc= 0.52857 val_loss= 0.70254 val_acc= 0.44262 time= 0.01300
Epoch: 0022 train_loss= 0.69327 train_acc= 0.52857 val_loss= 0.70233 val_acc= 0.44262 time= 0.01500
Epoch: 0023 train_loss= 0.69238 train_acc= 0.52857 val_loss= 0.70229 val_acc= 0.44262 time= 0.01400
Epoch: 0024 train_loss= 0.69237 train_acc= 0.52857 val_loss= 0.70241 val_acc= 0.44262 time= 0.01500
Epoch: 0025 train_loss= 0.69293 train_acc= 0.52857 val_loss= 0.70249 val_acc= 0.44262 time= 0.01400
Epoch: 0026 train_loss= 0.69228 train_acc= 0.52857 val_loss= 0.70267 val_acc= 0.44262 time= 0.01300
Epoch: 0027 train_loss= 0.69258 train_acc= 0.52857 val_loss= 0.70284 val_acc= 0.44262 time= 0.01400
Early stopping...
Optimization Finished!
Test set results: cost= 0.70100 accuracy= 0.44262 time= 0.00500 
