Epoch: 0001 train_loss= 0.69909 train_acc= 0.50000 val_loss= 0.69893 val_acc= 0.52459 time= 0.34377
Epoch: 0002 train_loss= 0.69829 train_acc= 0.52468 val_loss= 0.69865 val_acc= 0.52459 time= 0.01562
Epoch: 0003 train_loss= 0.69772 train_acc= 0.52468 val_loss= 0.69839 val_acc= 0.52459 time= 0.01563
Epoch: 0004 train_loss= 0.69707 train_acc= 0.52468 val_loss= 0.69819 val_acc= 0.52459 time= 0.02399
Epoch: 0005 train_loss= 0.69652 train_acc= 0.52468 val_loss= 0.69806 val_acc= 0.52459 time= 0.01591
Epoch: 0006 train_loss= 0.69602 train_acc= 0.52468 val_loss= 0.69800 val_acc= 0.52459 time= 0.01617
Epoch: 0007 train_loss= 0.69564 train_acc= 0.52468 val_loss= 0.69800 val_acc= 0.52459 time= 0.01606
Epoch: 0008 train_loss= 0.69530 train_acc= 0.52468 val_loss= 0.69813 val_acc= 0.52459 time= 0.01563
Epoch: 0009 train_loss= 0.69474 train_acc= 0.52468 val_loss= 0.69840 val_acc= 0.52459 time= 0.00000
Epoch: 0010 train_loss= 0.69409 train_acc= 0.52468 val_loss= 0.69880 val_acc= 0.52459 time= 0.00000
Epoch: 0011 train_loss= 0.69406 train_acc= 0.52468 val_loss= 0.69919 val_acc= 0.52459 time= 0.01563
Epoch: 0012 train_loss= 0.69381 train_acc= 0.52468 val_loss= 0.69950 val_acc= 0.52459 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69363 accuracy= 0.54098 time= 0.01563 
