Epoch: 0001 train_loss= 0.69649 train_acc= 0.51455 val_loss= 0.69854 val_acc= 0.52459 time= 0.64046
Epoch: 0002 train_loss= 0.69528 train_acc= 0.52364 val_loss= 0.70059 val_acc= 0.49180 time= 0.00000
Epoch: 0003 train_loss= 0.69147 train_acc= 0.51455 val_loss= 0.70180 val_acc= 0.49180 time= 0.01562
Epoch: 0004 train_loss= 0.69085 train_acc= 0.51818 val_loss= 0.70284 val_acc= 0.49180 time= 0.00000
Epoch: 0005 train_loss= 0.69396 train_acc= 0.52545 val_loss= 0.70369 val_acc= 0.49180 time= 0.00000
Epoch: 0006 train_loss= 0.69100 train_acc= 0.52545 val_loss= 0.70355 val_acc= 0.49180 time= 0.01563
Epoch: 0007 train_loss= 0.69299 train_acc= 0.52909 val_loss= 0.70249 val_acc= 0.49180 time= 0.00000
Epoch: 0008 train_loss= 0.69382 train_acc= 0.52545 val_loss= 0.70139 val_acc= 0.49180 time= 0.00000
Epoch: 0009 train_loss= 0.69347 train_acc= 0.50545 val_loss= 0.70017 val_acc= 0.49180 time= 0.01563
Epoch: 0010 train_loss= 0.69435 train_acc= 0.50545 val_loss= 0.69924 val_acc= 0.49180 time= 0.00000
Epoch: 0011 train_loss= 0.69356 train_acc= 0.52182 val_loss= 0.69836 val_acc= 0.49180 time= 0.01563
Epoch: 0012 train_loss= 0.69205 train_acc= 0.51636 val_loss= 0.69790 val_acc= 0.49180 time= 0.00000
Epoch: 0013 train_loss= 0.69424 train_acc= 0.51636 val_loss= 0.69752 val_acc= 0.49180 time= 0.00000
Epoch: 0014 train_loss= 0.69322 train_acc= 0.48182 val_loss= 0.69731 val_acc= 0.49180 time= 0.01563
Epoch: 0015 train_loss= 0.69276 train_acc= 0.52364 val_loss= 0.69731 val_acc= 0.49180 time= 0.00555
Epoch: 0016 train_loss= 0.69408 train_acc= 0.49273 val_loss= 0.69754 val_acc= 0.49180 time= 0.00000
Epoch: 0017 train_loss= 0.69357 train_acc= 0.50545 val_loss= 0.69804 val_acc= 0.49180 time= 0.01050
Epoch: 0018 train_loss= 0.69376 train_acc= 0.52545 val_loss= 0.69847 val_acc= 0.49180 time= 0.00000
Epoch: 0019 train_loss= 0.69372 train_acc= 0.52545 val_loss= 0.69876 val_acc= 0.49180 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.69339 accuracy= 0.53279 time= 0.01563 
