Epoch: 0001 train_loss= 0.69971 train_acc= 0.47879 val_loss= 0.69860 val_acc= 0.51613 time= 0.12501
Epoch: 0002 train_loss= 0.69850 train_acc= 0.52121 val_loss= 0.69797 val_acc= 0.51613 time= 0.01563
Epoch: 0003 train_loss= 0.69790 train_acc= 0.52424 val_loss= 0.69748 val_acc= 0.51613 time= 0.00000
Epoch: 0004 train_loss= 0.69720 train_acc= 0.52424 val_loss= 0.69702 val_acc= 0.51613 time= 0.01563
Epoch: 0005 train_loss= 0.69664 train_acc= 0.52424 val_loss= 0.69661 val_acc= 0.51613 time= 0.01562
Epoch: 0006 train_loss= 0.69628 train_acc= 0.52424 val_loss= 0.69624 val_acc= 0.51613 time= 0.01563
Epoch: 0007 train_loss= 0.69570 train_acc= 0.52424 val_loss= 0.69592 val_acc= 0.51613 time= 0.01563
Epoch: 0008 train_loss= 0.69525 train_acc= 0.52424 val_loss= 0.69564 val_acc= 0.51613 time= 0.00000
Epoch: 0009 train_loss= 0.69471 train_acc= 0.52424 val_loss= 0.69541 val_acc= 0.51613 time= 0.01563
Epoch: 0010 train_loss= 0.69484 train_acc= 0.52424 val_loss= 0.69520 val_acc= 0.51613 time= 0.01563
Epoch: 0011 train_loss= 0.69404 train_acc= 0.52424 val_loss= 0.69503 val_acc= 0.51613 time= 0.01563
Epoch: 0012 train_loss= 0.69380 train_acc= 0.52424 val_loss= 0.69487 val_acc= 0.51613 time= 0.00000
Epoch: 0013 train_loss= 0.69428 train_acc= 0.52424 val_loss= 0.69471 val_acc= 0.51613 time= 0.01562
Epoch: 0014 train_loss= 0.69396 train_acc= 0.52424 val_loss= 0.69453 val_acc= 0.51613 time= 0.01563
Epoch: 0015 train_loss= 0.69366 train_acc= 0.52424 val_loss= 0.69434 val_acc= 0.51613 time= 0.01563
Epoch: 0016 train_loss= 0.69346 train_acc= 0.52424 val_loss= 0.69414 val_acc= 0.51613 time= 0.00000
Epoch: 0017 train_loss= 0.69340 train_acc= 0.52424 val_loss= 0.69394 val_acc= 0.51613 time= 0.01563
Epoch: 0018 train_loss= 0.69286 train_acc= 0.52424 val_loss= 0.69374 val_acc= 0.51613 time= 0.01563
Epoch: 0019 train_loss= 0.69242 train_acc= 0.52424 val_loss= 0.69355 val_acc= 0.51613 time= 0.01563
Epoch: 0020 train_loss= 0.69258 train_acc= 0.52424 val_loss= 0.69339 val_acc= 0.51613 time= 0.00000
Epoch: 0021 train_loss= 0.69237 train_acc= 0.52424 val_loss= 0.69325 val_acc= 0.51613 time= 0.01563
Epoch: 0022 train_loss= 0.69217 train_acc= 0.52424 val_loss= 0.69312 val_acc= 0.51613 time= 0.01563
Epoch: 0023 train_loss= 0.69241 train_acc= 0.52424 val_loss= 0.69301 val_acc= 0.51613 time= 0.01563
Epoch: 0024 train_loss= 0.69256 train_acc= 0.52424 val_loss= 0.69292 val_acc= 0.51613 time= 0.01563
Epoch: 0025 train_loss= 0.69220 train_acc= 0.52424 val_loss= 0.69284 val_acc= 0.51613 time= 0.00000
Epoch: 0026 train_loss= 0.69202 train_acc= 0.52424 val_loss= 0.69277 val_acc= 0.51613 time= 0.01563
Epoch: 0027 train_loss= 0.69206 train_acc= 0.52424 val_loss= 0.69272 val_acc= 0.51613 time= 0.01563
Epoch: 0028 train_loss= 0.69211 train_acc= 0.52424 val_loss= 0.69269 val_acc= 0.51613 time= 0.01563
Epoch: 0029 train_loss= 0.69166 train_acc= 0.52424 val_loss= 0.69266 val_acc= 0.51613 time= 0.00000
Epoch: 0030 train_loss= 0.69196 train_acc= 0.52424 val_loss= 0.69265 val_acc= 0.51613 time= 0.01562
Epoch: 0031 train_loss= 0.69147 train_acc= 0.52424 val_loss= 0.69265 val_acc= 0.51613 time= 0.01563
Epoch: 0032 train_loss= 0.69141 train_acc= 0.52424 val_loss= 0.69267 val_acc= 0.51613 time= 0.01563
Epoch: 0033 train_loss= 0.69178 train_acc= 0.52424 val_loss= 0.69271 val_acc= 0.51613 time= 0.00000
Epoch: 0034 train_loss= 0.69170 train_acc= 0.52424 val_loss= 0.69275 val_acc= 0.51613 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.70196 accuracy= 0.44355 time= 0.01563 
