Epoch: 0001 train_loss= 0.69913 train_acc= 0.52121 val_loss= 0.69858 val_acc= 0.54098 time= 0.12501
Epoch: 0002 train_loss= 0.69857 train_acc= 0.52727 val_loss= 0.69802 val_acc= 0.54098 time= 0.00000
Epoch: 0003 train_loss= 0.69833 train_acc= 0.49091 val_loss= 0.69751 val_acc= 0.54098 time= 0.01563
Epoch: 0004 train_loss= 0.69782 train_acc= 0.49091 val_loss= 0.69703 val_acc= 0.54098 time= 0.01563
Epoch: 0005 train_loss= 0.69723 train_acc= 0.51818 val_loss= 0.69662 val_acc= 0.54098 time= 0.01563
Epoch: 0006 train_loss= 0.69678 train_acc= 0.50606 val_loss= 0.69622 val_acc= 0.54098 time= 0.01563
Epoch: 0007 train_loss= 0.69641 train_acc= 0.51212 val_loss= 0.69584 val_acc= 0.54098 time= 0.01563
Epoch: 0008 train_loss= 0.69593 train_acc= 0.49697 val_loss= 0.69549 val_acc= 0.54098 time= 0.01563
Epoch: 0009 train_loss= 0.69565 train_acc= 0.50303 val_loss= 0.69517 val_acc= 0.54098 time= 0.00000
Epoch: 0010 train_loss= 0.69529 train_acc= 0.50000 val_loss= 0.69487 val_acc= 0.54098 time= 0.01563
Epoch: 0011 train_loss= 0.69496 train_acc= 0.51818 val_loss= 0.69462 val_acc= 0.54098 time= 0.01563
Epoch: 0012 train_loss= 0.69472 train_acc= 0.50303 val_loss= 0.69439 val_acc= 0.54098 time= 0.01562
Epoch: 0013 train_loss= 0.69476 train_acc= 0.50606 val_loss= 0.69421 val_acc= 0.54098 time= 0.00000
Epoch: 0014 train_loss= 0.69461 train_acc= 0.50000 val_loss= 0.69405 val_acc= 0.54098 time= 0.01563
Epoch: 0015 train_loss= 0.69426 train_acc= 0.50909 val_loss= 0.69390 val_acc= 0.54098 time= 0.01563
Epoch: 0016 train_loss= 0.69427 train_acc= 0.50303 val_loss= 0.69377 val_acc= 0.54098 time= 0.01563
Epoch: 0017 train_loss= 0.69417 train_acc= 0.49697 val_loss= 0.69367 val_acc= 0.54098 time= 0.00000
Epoch: 0018 train_loss= 0.69398 train_acc= 0.50000 val_loss= 0.69362 val_acc= 0.54098 time= 0.01563
Epoch: 0019 train_loss= 0.69373 train_acc= 0.50000 val_loss= 0.69356 val_acc= 0.54098 time= 0.01563
Epoch: 0020 train_loss= 0.69393 train_acc= 0.50000 val_loss= 0.69348 val_acc= 0.54098 time= 0.00000
Epoch: 0021 train_loss= 0.69361 train_acc= 0.50606 val_loss= 0.69336 val_acc= 0.54098 time= 0.01563
Epoch: 0022 train_loss= 0.69368 train_acc= 0.51212 val_loss= 0.69324 val_acc= 0.54098 time= 0.01562
Epoch: 0023 train_loss= 0.69335 train_acc= 0.50909 val_loss= 0.69313 val_acc= 0.54098 time= 0.01563
Epoch: 0024 train_loss= 0.69339 train_acc= 0.50303 val_loss= 0.69304 val_acc= 0.54098 time= 0.00000
Epoch: 0025 train_loss= 0.69337 train_acc= 0.50303 val_loss= 0.69297 val_acc= 0.54098 time= 0.01563
Epoch: 0026 train_loss= 0.69341 train_acc= 0.49697 val_loss= 0.69290 val_acc= 0.54098 time= 0.01563
Epoch: 0027 train_loss= 0.69350 train_acc= 0.49697 val_loss= 0.69287 val_acc= 0.54098 time= 0.00000
Epoch: 0028 train_loss= 0.69320 train_acc= 0.49697 val_loss= 0.69284 val_acc= 0.54098 time= 0.01563
Epoch: 0029 train_loss= 0.69329 train_acc= 0.50000 val_loss= 0.69282 val_acc= 0.54098 time= 0.01563
Epoch: 0030 train_loss= 0.69319 train_acc= 0.50000 val_loss= 0.69281 val_acc= 0.54098 time= 0.01563
Epoch: 0031 train_loss= 0.69312 train_acc= 0.50000 val_loss= 0.69280 val_acc= 0.54098 time= 0.00000
Epoch: 0032 train_loss= 0.69314 train_acc= 0.50000 val_loss= 0.69281 val_acc= 0.54098 time= 0.01563
Epoch: 0033 train_loss= 0.69331 train_acc= 0.50000 val_loss= 0.69283 val_acc= 0.54098 time= 0.01563
Epoch: 0034 train_loss= 0.69302 train_acc= 0.49697 val_loss= 0.69286 val_acc= 0.54098 time= 0.00000
Epoch: 0035 train_loss= 0.69315 train_acc= 0.50000 val_loss= 0.69289 val_acc= 0.54098 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69255 accuracy= 0.54918 time= 0.00000 
