Epoch: 0001 train_loss= 0.69857 train_acc= 0.51818 val_loss= 0.69939 val_acc= 0.48387 time= 0.07812
Epoch: 0002 train_loss= 0.69759 train_acc= 0.52424 val_loss= 0.69942 val_acc= 0.48387 time= 0.01563
Epoch: 0003 train_loss= 0.69683 train_acc= 0.51818 val_loss= 0.69957 val_acc= 0.48387 time= 0.00000
Epoch: 0004 train_loss= 0.69675 train_acc= 0.51818 val_loss= 0.69973 val_acc= 0.48387 time= 0.01562
Epoch: 0005 train_loss= 0.69622 train_acc= 0.51818 val_loss= 0.69985 val_acc= 0.48387 time= 0.01563
Epoch: 0006 train_loss= 0.69588 train_acc= 0.51818 val_loss= 0.69994 val_acc= 0.48387 time= 0.00000
Epoch: 0007 train_loss= 0.69535 train_acc= 0.51818 val_loss= 0.70002 val_acc= 0.48387 time= 0.01562
Epoch: 0008 train_loss= 0.69512 train_acc= 0.51818 val_loss= 0.69994 val_acc= 0.48387 time= 0.01563
Epoch: 0009 train_loss= 0.69518 train_acc= 0.51818 val_loss= 0.69966 val_acc= 0.48387 time= 0.00000
Epoch: 0010 train_loss= 0.69396 train_acc= 0.51818 val_loss= 0.69934 val_acc= 0.48387 time= 0.01562
Epoch: 0011 train_loss= 0.69433 train_acc= 0.51818 val_loss= 0.69895 val_acc= 0.48387 time= 0.01563
Epoch: 0012 train_loss= 0.69382 train_acc= 0.52121 val_loss= 0.69858 val_acc= 0.48387 time= 0.01563
Epoch: 0013 train_loss= 0.69363 train_acc= 0.51818 val_loss= 0.69820 val_acc= 0.48387 time= 0.00000
Epoch: 0014 train_loss= 0.69342 train_acc= 0.51818 val_loss= 0.69804 val_acc= 0.48387 time= 0.01563
Epoch: 0015 train_loss= 0.69288 train_acc= 0.52121 val_loss= 0.69799 val_acc= 0.48387 time= 0.01563
Epoch: 0016 train_loss= 0.69387 train_acc= 0.51818 val_loss= 0.69786 val_acc= 0.48387 time= 0.00000
Epoch: 0017 train_loss= 0.69331 train_acc= 0.51818 val_loss= 0.69759 val_acc= 0.48387 time= 0.01563
Epoch: 0018 train_loss= 0.69324 train_acc= 0.51818 val_loss= 0.69733 val_acc= 0.48387 time= 0.01563
Epoch: 0019 train_loss= 0.69304 train_acc= 0.51818 val_loss= 0.69708 val_acc= 0.48387 time= 0.00000
Epoch: 0020 train_loss= 0.69296 train_acc= 0.52121 val_loss= 0.69687 val_acc= 0.48387 time= 0.01563
Epoch: 0021 train_loss= 0.69296 train_acc= 0.51818 val_loss= 0.69668 val_acc= 0.48387 time= 0.01563
Epoch: 0022 train_loss= 0.69229 train_acc= 0.51818 val_loss= 0.69654 val_acc= 0.48387 time= 0.00000
Epoch: 0023 train_loss= 0.69218 train_acc= 0.51818 val_loss= 0.69643 val_acc= 0.48387 time= 0.01563
Epoch: 0024 train_loss= 0.69238 train_acc= 0.51818 val_loss= 0.69634 val_acc= 0.48387 time= 0.01562
Epoch: 0025 train_loss= 0.69238 train_acc= 0.51818 val_loss= 0.69633 val_acc= 0.48387 time= 0.01563
Epoch: 0026 train_loss= 0.69195 train_acc= 0.52121 val_loss= 0.69648 val_acc= 0.48387 time= 0.00000
Epoch: 0027 train_loss= 0.69291 train_acc= 0.51818 val_loss= 0.69660 val_acc= 0.48387 time= 0.01563
Epoch: 0028 train_loss= 0.69205 train_acc= 0.51818 val_loss= 0.69664 val_acc= 0.48387 time= 0.01563
Epoch: 0029 train_loss= 0.69148 train_acc= 0.52121 val_loss= 0.69664 val_acc= 0.48387 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.68722 accuracy= 0.55645 time= 0.00000 
