Epoch: 0001 train_loss= 0.71718 train_acc= 0.45974 val_loss= 0.69944 val_acc= 0.59016 time= 0.77192
Epoch: 0002 train_loss= 0.71514 train_acc= 0.46104 val_loss= 0.69787 val_acc= 0.59016 time= 0.00000
Epoch: 0003 train_loss= 0.71176 train_acc= 0.45844 val_loss= 0.69665 val_acc= 0.59016 time= 0.00000
Epoch: 0004 train_loss= 0.70615 train_acc= 0.45974 val_loss= 0.69577 val_acc= 0.59016 time= 0.01563
Epoch: 0005 train_loss= 0.70363 train_acc= 0.45974 val_loss= 0.69520 val_acc= 0.59016 time= 0.00000
Epoch: 0006 train_loss= 0.70088 train_acc= 0.45844 val_loss= 0.69491 val_acc= 0.59016 time= 0.01563
Epoch: 0007 train_loss= 0.69957 train_acc= 0.45844 val_loss= 0.69485 val_acc= 0.59016 time= 0.00000
Epoch: 0008 train_loss= 0.69797 train_acc= 0.45714 val_loss= 0.69501 val_acc= 0.59016 time= 0.00000
Epoch: 0009 train_loss= 0.69739 train_acc= 0.46883 val_loss= 0.69536 val_acc= 0.42623 time= 0.01562
Epoch: 0010 train_loss= 0.69578 train_acc= 0.50519 val_loss= 0.69587 val_acc= 0.40984 time= 0.00000
Epoch: 0011 train_loss= 0.69469 train_acc= 0.51688 val_loss= 0.69643 val_acc= 0.40984 time= 0.00000
Epoch: 0012 train_loss= 0.69422 train_acc= 0.52987 val_loss= 0.69708 val_acc= 0.40984 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69331 accuracy= 0.52459 time= 0.00000 
