Epoch: 0001 train_loss= 0.69937 train_acc= 0.51091 val_loss= 0.69813 val_acc= 0.60656 time= 0.38310
Epoch: 0002 train_loss= 0.69882 train_acc= 0.49636 val_loss= 0.69789 val_acc= 0.60656 time= 0.00000
Epoch: 0003 train_loss= 0.69832 train_acc= 0.48727 val_loss= 0.69759 val_acc= 0.60656 time= 0.01563
Epoch: 0004 train_loss= 0.69778 train_acc= 0.51636 val_loss= 0.69729 val_acc= 0.39344 time= 0.01833
Epoch: 0005 train_loss= 0.69730 train_acc= 0.51273 val_loss= 0.69697 val_acc= 0.39344 time= 0.01563
Epoch: 0006 train_loss= 0.69691 train_acc= 0.50000 val_loss= 0.69668 val_acc= 0.39344 time= 0.00000
Epoch: 0007 train_loss= 0.69653 train_acc= 0.46182 val_loss= 0.69632 val_acc= 0.39344 time= 0.01563
Epoch: 0008 train_loss= 0.69605 train_acc= 0.50909 val_loss= 0.69594 val_acc= 0.39344 time= 0.01563
Epoch: 0009 train_loss= 0.69578 train_acc= 0.48727 val_loss= 0.69557 val_acc= 0.39344 time= 0.01563
Epoch: 0010 train_loss= 0.69542 train_acc= 0.49818 val_loss= 0.69525 val_acc= 0.39344 time= 0.01563
Epoch: 0011 train_loss= 0.69525 train_acc= 0.48182 val_loss= 0.69487 val_acc= 0.60656 time= 0.00000
Epoch: 0012 train_loss= 0.69492 train_acc= 0.51091 val_loss= 0.69451 val_acc= 0.60656 time= 0.01562
Epoch: 0013 train_loss= 0.69465 train_acc= 0.51273 val_loss= 0.69418 val_acc= 0.60656 time= 0.01563
Epoch: 0014 train_loss= 0.69453 train_acc= 0.50545 val_loss= 0.69394 val_acc= 0.60656 time= 0.01563
Epoch: 0015 train_loss= 0.69433 train_acc= 0.50182 val_loss= 0.69367 val_acc= 0.60656 time= 0.01563
Epoch: 0016 train_loss= 0.69413 train_acc= 0.51818 val_loss= 0.69344 val_acc= 0.60656 time= 0.00000
Epoch: 0017 train_loss= 0.69398 train_acc= 0.51636 val_loss= 0.69324 val_acc= 0.60656 time= 0.01562
Epoch: 0018 train_loss= 0.69391 train_acc= 0.50182 val_loss= 0.69311 val_acc= 0.60656 time= 0.01563
Epoch: 0019 train_loss= 0.69378 train_acc= 0.49818 val_loss= 0.69306 val_acc= 0.60656 time= 0.01563
Epoch: 0020 train_loss= 0.69373 train_acc= 0.50182 val_loss= 0.69315 val_acc= 0.60656 time= 0.01562
Epoch: 0021 train_loss= 0.69361 train_acc= 0.51091 val_loss= 0.69324 val_acc= 0.60656 time= 0.00000
Epoch: 0022 train_loss= 0.69355 train_acc= 0.49091 val_loss= 0.69336 val_acc= 0.60656 time= 0.01563
Epoch: 0023 train_loss= 0.69348 train_acc= 0.50364 val_loss= 0.69333 val_acc= 0.60656 time= 0.01563
Epoch: 0024 train_loss= 0.69344 train_acc= 0.48364 val_loss= 0.69349 val_acc= 0.39344 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69340 accuracy= 0.45902 time= 0.00000 
