Epoch: 0001 train_loss= 0.69913 train_acc= 0.51091 val_loss= 0.69855 val_acc= 0.52459 time= 0.20427
Epoch: 0002 train_loss= 0.69840 train_acc= 0.49273 val_loss= 0.69820 val_acc= 0.52459 time= 0.00000
Epoch: 0003 train_loss= 0.69773 train_acc= 0.50364 val_loss= 0.69785 val_acc= 0.52459 time= 0.01563
Epoch: 0004 train_loss= 0.69762 train_acc= 0.49273 val_loss= 0.69749 val_acc= 0.52459 time= 0.01563
Epoch: 0005 train_loss= 0.69720 train_acc= 0.49636 val_loss= 0.69709 val_acc= 0.52459 time= 0.01563
Epoch: 0006 train_loss= 0.69660 train_acc= 0.49091 val_loss= 0.69668 val_acc= 0.52459 time= 0.00000
Epoch: 0007 train_loss= 0.69624 train_acc= 0.48909 val_loss= 0.69629 val_acc= 0.52459 time= 0.01563
Epoch: 0008 train_loss= 0.69595 train_acc= 0.49455 val_loss= 0.69592 val_acc= 0.52459 time= 0.01563
Epoch: 0009 train_loss= 0.69561 train_acc= 0.49455 val_loss= 0.69556 val_acc= 0.52459 time= 0.01563
Epoch: 0010 train_loss= 0.69517 train_acc= 0.50000 val_loss= 0.69524 val_acc= 0.52459 time= 0.01563
Epoch: 0011 train_loss= 0.69500 train_acc= 0.49636 val_loss= 0.69494 val_acc= 0.52459 time= 0.00000
Epoch: 0012 train_loss= 0.69475 train_acc= 0.49818 val_loss= 0.69469 val_acc= 0.52459 time= 0.01563
Epoch: 0013 train_loss= 0.69459 train_acc= 0.49091 val_loss= 0.69447 val_acc= 0.52459 time= 0.01562
Epoch: 0014 train_loss= 0.69434 train_acc= 0.49636 val_loss= 0.69428 val_acc= 0.52459 time= 0.01563
Epoch: 0015 train_loss= 0.69421 train_acc= 0.48182 val_loss= 0.69414 val_acc= 0.52459 time= 0.01563
Epoch: 0016 train_loss= 0.69409 train_acc= 0.50000 val_loss= 0.69402 val_acc= 0.52459 time= 0.00000
Epoch: 0017 train_loss= 0.69397 train_acc= 0.49636 val_loss= 0.69392 val_acc= 0.52459 time= 0.01562
Epoch: 0018 train_loss= 0.69390 train_acc= 0.50000 val_loss= 0.69385 val_acc= 0.52459 time= 0.01563
Epoch: 0019 train_loss= 0.69364 train_acc= 0.49091 val_loss= 0.69380 val_acc= 0.52459 time= 0.01563
Epoch: 0020 train_loss= 0.69353 train_acc= 0.49091 val_loss= 0.69373 val_acc= 0.52459 time= 0.01563
Epoch: 0021 train_loss= 0.69342 train_acc= 0.49091 val_loss= 0.69368 val_acc= 0.52459 time= 0.00000
Epoch: 0022 train_loss= 0.69345 train_acc= 0.49273 val_loss= 0.69367 val_acc= 0.52459 time= 0.01563
Epoch: 0023 train_loss= 0.69337 train_acc= 0.49273 val_loss= 0.69368 val_acc= 0.52459 time= 0.01562
Epoch: 0024 train_loss= 0.69339 train_acc= 0.49273 val_loss= 0.69369 val_acc= 0.52459 time= 0.01563
Epoch: 0025 train_loss= 0.69331 train_acc= 0.49273 val_loss= 0.69371 val_acc= 0.52459 time= 0.01562
Epoch: 0026 train_loss= 0.69326 train_acc= 0.49273 val_loss= 0.69371 val_acc= 0.52459 time= 0.00000
Epoch: 0027 train_loss= 0.69331 train_acc= 0.49273 val_loss= 0.69363 val_acc= 0.52459 time= 0.01563
Epoch: 0028 train_loss= 0.69319 train_acc= 0.49273 val_loss= 0.69357 val_acc= 0.52459 time= 0.01563
Epoch: 0029 train_loss= 0.69320 train_acc= 0.49455 val_loss= 0.69350 val_acc= 0.52459 time= 0.01563
Epoch: 0030 train_loss= 0.69332 train_acc= 0.49273 val_loss= 0.69341 val_acc= 0.52459 time= 0.01563
Epoch: 0031 train_loss= 0.69316 train_acc= 0.49273 val_loss= 0.69333 val_acc= 0.52459 time= 0.00000
Epoch: 0032 train_loss= 0.69319 train_acc= 0.49455 val_loss= 0.69327 val_acc= 0.52459 time= 0.01563
Epoch: 0033 train_loss= 0.69326 train_acc= 0.47455 val_loss= 0.69324 val_acc= 0.52459 time= 0.01563
Epoch: 0034 train_loss= 0.69315 train_acc= 0.51273 val_loss= 0.69324 val_acc= 0.52459 time= 0.01563
Epoch: 0035 train_loss= 0.69314 train_acc= 0.50545 val_loss= 0.69327 val_acc= 0.52459 time= 0.00000
Epoch: 0036 train_loss= 0.69324 train_acc= 0.49636 val_loss= 0.69329 val_acc= 0.52459 time= 0.01563
Epoch: 0037 train_loss= 0.69322 train_acc= 0.49273 val_loss= 0.69333 val_acc= 0.52459 time= 0.01563
Epoch: 0038 train_loss= 0.69323 train_acc= 0.49091 val_loss= 0.69336 val_acc= 0.52459 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69373 accuracy= 0.46721 time= 0.00000 
