Epoch: 0001 train_loss= 0.69894 train_acc= 0.50545 val_loss= 0.69970 val_acc= 0.45161 time= 0.21877
Epoch: 0002 train_loss= 0.69830 train_acc= 0.51091 val_loss= 0.69938 val_acc= 0.45161 time= 0.01563
Epoch: 0003 train_loss= 0.69790 train_acc= 0.50000 val_loss= 0.69904 val_acc= 0.45161 time= 0.01563
Epoch: 0004 train_loss= 0.69731 train_acc= 0.50545 val_loss= 0.69873 val_acc= 0.45161 time= 0.01563
Epoch: 0005 train_loss= 0.69689 train_acc= 0.50545 val_loss= 0.69844 val_acc= 0.45161 time= 0.01563
Epoch: 0006 train_loss= 0.69651 train_acc= 0.50545 val_loss= 0.69816 val_acc= 0.45161 time= 0.00000
Epoch: 0007 train_loss= 0.69602 train_acc= 0.50545 val_loss= 0.69796 val_acc= 0.45161 time= 0.01563
Epoch: 0008 train_loss= 0.69575 train_acc= 0.50545 val_loss= 0.69776 val_acc= 0.45161 time= 0.01563
Epoch: 0009 train_loss= 0.69540 train_acc= 0.50545 val_loss= 0.69756 val_acc= 0.45161 time= 0.01563
Epoch: 0010 train_loss= 0.69502 train_acc= 0.50545 val_loss= 0.69744 val_acc= 0.45161 time= 0.00000
Epoch: 0011 train_loss= 0.69487 train_acc= 0.50545 val_loss= 0.69725 val_acc= 0.45161 time= 0.01563
Epoch: 0012 train_loss= 0.69445 train_acc= 0.50545 val_loss= 0.69716 val_acc= 0.45161 time= 0.01563
Epoch: 0013 train_loss= 0.69422 train_acc= 0.50545 val_loss= 0.69726 val_acc= 0.45161 time= 0.01563
Epoch: 0014 train_loss= 0.69427 train_acc= 0.50545 val_loss= 0.69729 val_acc= 0.45161 time= 0.01563
Epoch: 0015 train_loss= 0.69405 train_acc= 0.50545 val_loss= 0.69733 val_acc= 0.45161 time= 0.00000
Epoch: 0016 train_loss= 0.69382 train_acc= 0.50545 val_loss= 0.69738 val_acc= 0.45161 time= 0.01563
Epoch: 0017 train_loss= 0.69375 train_acc= 0.50545 val_loss= 0.69737 val_acc= 0.45161 time= 0.01563
Epoch: 0018 train_loss= 0.69363 train_acc= 0.50545 val_loss= 0.69727 val_acc= 0.45161 time= 0.01563
Epoch: 0019 train_loss= 0.69367 train_acc= 0.50545 val_loss= 0.69701 val_acc= 0.45161 time= 0.00000
Epoch: 0020 train_loss= 0.69348 train_acc= 0.50545 val_loss= 0.69670 val_acc= 0.45161 time= 0.01563
Epoch: 0021 train_loss= 0.69343 train_acc= 0.50545 val_loss= 0.69639 val_acc= 0.45161 time= 0.01563
Epoch: 0022 train_loss= 0.69334 train_acc= 0.50545 val_loss= 0.69605 val_acc= 0.45161 time= 0.01563
Epoch: 0023 train_loss= 0.69314 train_acc= 0.50727 val_loss= 0.69592 val_acc= 0.45161 time= 0.01563
Epoch: 0024 train_loss= 0.69323 train_acc= 0.50545 val_loss= 0.69585 val_acc= 0.45161 time= 0.00000
Epoch: 0025 train_loss= 0.69318 train_acc= 0.50545 val_loss= 0.69582 val_acc= 0.45161 time= 0.01563
Epoch: 0026 train_loss= 0.69324 train_acc= 0.50545 val_loss= 0.69577 val_acc= 0.45161 time= 0.01563
Epoch: 0027 train_loss= 0.69309 train_acc= 0.50545 val_loss= 0.69582 val_acc= 0.45161 time= 0.01563
Epoch: 0028 train_loss= 0.69326 train_acc= 0.50545 val_loss= 0.69582 val_acc= 0.45161 time= 0.00000
Epoch: 0029 train_loss= 0.69318 train_acc= 0.50545 val_loss= 0.69581 val_acc= 0.45161 time= 0.01563
Epoch: 0030 train_loss= 0.69308 train_acc= 0.50545 val_loss= 0.69575 val_acc= 0.45161 time= 0.01563
Epoch: 0031 train_loss= 0.69299 train_acc= 0.50545 val_loss= 0.69580 val_acc= 0.45161 time= 0.01563
Epoch: 0032 train_loss= 0.69310 train_acc= 0.50545 val_loss= 0.69584 val_acc= 0.45161 time= 0.01563
Epoch: 0033 train_loss= 0.69299 train_acc= 0.50545 val_loss= 0.69595 val_acc= 0.45161 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69539 accuracy= 0.44355 time= 0.00000 
