Epoch: 0001 train_loss= 0.69879 train_acc= 0.50606 val_loss= 0.70006 val_acc= 0.40984 time= 0.12500
Epoch: 0002 train_loss= 0.69794 train_acc= 0.53030 val_loss= 0.70040 val_acc= 0.40984 time= 0.00000
Epoch: 0003 train_loss= 0.69766 train_acc= 0.52424 val_loss= 0.70040 val_acc= 0.40984 time= 0.01563
Epoch: 0004 train_loss= 0.69727 train_acc= 0.52424 val_loss= 0.70014 val_acc= 0.40984 time= 0.01563
Epoch: 0005 train_loss= 0.69661 train_acc= 0.52424 val_loss= 0.69982 val_acc= 0.40984 time= 0.01563
Epoch: 0006 train_loss= 0.69694 train_acc= 0.52424 val_loss= 0.69930 val_acc= 0.40984 time= 0.00000
Epoch: 0007 train_loss= 0.69609 train_acc= 0.52424 val_loss= 0.69864 val_acc= 0.40984 time= 0.01563
Epoch: 0008 train_loss= 0.69573 train_acc= 0.52424 val_loss= 0.69808 val_acc= 0.40984 time= 0.01563
Epoch: 0009 train_loss= 0.69536 train_acc= 0.52424 val_loss= 0.69771 val_acc= 0.40984 time= 0.01563
Epoch: 0010 train_loss= 0.69491 train_acc= 0.52424 val_loss= 0.69744 val_acc= 0.40984 time= 0.00000
Epoch: 0011 train_loss= 0.69497 train_acc= 0.52424 val_loss= 0.69722 val_acc= 0.40984 time= 0.01563
Epoch: 0012 train_loss= 0.69466 train_acc= 0.52424 val_loss= 0.69708 val_acc= 0.40984 time= 0.01563
Epoch: 0013 train_loss= 0.69451 train_acc= 0.52424 val_loss= 0.69697 val_acc= 0.40984 time= 0.01565
Epoch: 0014 train_loss= 0.69417 train_acc= 0.52424 val_loss= 0.69685 val_acc= 0.40984 time= 0.00000
Epoch: 0015 train_loss= 0.69402 train_acc= 0.52424 val_loss= 0.69675 val_acc= 0.40984 time= 0.01561
Epoch: 0016 train_loss= 0.69413 train_acc= 0.52424 val_loss= 0.69651 val_acc= 0.40984 time= 0.01563
Epoch: 0017 train_loss= 0.69360 train_acc= 0.52424 val_loss= 0.69632 val_acc= 0.40984 time= 0.01563
Epoch: 0018 train_loss= 0.69352 train_acc= 0.52424 val_loss= 0.69612 val_acc= 0.40984 time= 0.01563
Epoch: 0019 train_loss= 0.69335 train_acc= 0.52424 val_loss= 0.69587 val_acc= 0.40984 time= 0.00000
Epoch: 0020 train_loss= 0.69328 train_acc= 0.52424 val_loss= 0.69567 val_acc= 0.40984 time= 0.01563
Epoch: 0021 train_loss= 0.69350 train_acc= 0.52424 val_loss= 0.69555 val_acc= 0.40984 time= 0.01563
Epoch: 0022 train_loss= 0.69316 train_acc= 0.52424 val_loss= 0.69582 val_acc= 0.40984 time= 0.01563
Epoch: 0023 train_loss= 0.69303 train_acc= 0.52424 val_loss= 0.69610 val_acc= 0.40984 time= 0.00000
Epoch: 0024 train_loss= 0.69306 train_acc= 0.52424 val_loss= 0.69635 val_acc= 0.40984 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.69521 accuracy= 0.46721 time= 0.00000 
