Epoch: 0001 train_loss= 0.70094 train_acc= 0.50000 val_loss= 0.69821 val_acc= 0.52459 time= 0.12501
Epoch: 0002 train_loss= 0.69797 train_acc= 0.50000 val_loss= 0.69623 val_acc= 0.52459 time= 0.01562
Epoch: 0003 train_loss= 0.69565 train_acc= 0.50303 val_loss= 0.69498 val_acc= 0.52459 time= 0.00000
Epoch: 0004 train_loss= 0.69404 train_acc= 0.50303 val_loss= 0.69432 val_acc= 0.52459 time= 0.01563
Epoch: 0005 train_loss= 0.69291 train_acc= 0.50000 val_loss= 0.69409 val_acc= 0.52459 time= 0.01563
Epoch: 0006 train_loss= 0.69243 train_acc= 0.49697 val_loss= 0.69414 val_acc= 0.52459 time= 0.00000
Epoch: 0007 train_loss= 0.69224 train_acc= 0.49697 val_loss= 0.69435 val_acc= 0.52459 time= 0.01563
Epoch: 0008 train_loss= 0.69182 train_acc= 0.50000 val_loss= 0.69466 val_acc= 0.54098 time= 0.01563
Epoch: 0009 train_loss= 0.69151 train_acc= 0.50303 val_loss= 0.69501 val_acc= 0.54098 time= 0.00000
Epoch: 0010 train_loss= 0.69196 train_acc= 0.50303 val_loss= 0.69533 val_acc= 0.54098 time= 0.01563
Epoch: 0011 train_loss= 0.69121 train_acc= 0.50303 val_loss= 0.69559 val_acc= 0.54098 time= 0.00000
Epoch: 0012 train_loss= 0.69083 train_acc= 0.50909 val_loss= 0.69580 val_acc= 0.54098 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 0.68889 accuracy= 0.56557 time= 0.00000 
