Epoch: 0001 train_loss= 0.69956 train_acc= 0.48909 val_loss= 0.69899 val_acc= 0.41935 time= 0.39065
Epoch: 0002 train_loss= 0.69914 train_acc= 0.48545 val_loss= 0.69688 val_acc= 0.58065 time= 0.01939
Epoch: 0003 train_loss= 0.69869 train_acc= 0.51273 val_loss= 0.69570 val_acc= 0.58065 time= 0.00800
Epoch: 0004 train_loss= 0.69832 train_acc= 0.51273 val_loss= 0.69508 val_acc= 0.58065 time= 0.00000
Epoch: 0005 train_loss= 0.69779 train_acc= 0.51818 val_loss= 0.69481 val_acc= 0.58065 time= 0.01567
Epoch: 0006 train_loss= 0.69710 train_acc= 0.51636 val_loss= 0.69462 val_acc= 0.58065 time= 0.01563
Epoch: 0007 train_loss= 0.69694 train_acc= 0.52000 val_loss= 0.69465 val_acc= 0.58065 time= 0.00000
Epoch: 0008 train_loss= 0.69676 train_acc= 0.50909 val_loss= 0.69470 val_acc= 0.58065 time= 0.01563
Epoch: 0009 train_loss= 0.69629 train_acc= 0.52000 val_loss= 0.69485 val_acc= 0.58065 time= 0.01562
Epoch: 0010 train_loss= 0.69585 train_acc= 0.51636 val_loss= 0.69495 val_acc= 0.58065 time= 0.01563
Epoch: 0011 train_loss= 0.69536 train_acc= 0.51273 val_loss= 0.69502 val_acc= 0.58065 time= 0.00000
Epoch: 0012 train_loss= 0.69527 train_acc= 0.50182 val_loss= 0.69506 val_acc= 0.58065 time= 0.01563
Epoch: 0013 train_loss= 0.69508 train_acc= 0.50727 val_loss= 0.69505 val_acc= 0.41935 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69505 accuracy= 0.44355 time= 0.00000 
