Epoch: 0001 train_loss= 0.70025 train_acc= 0.45152 val_loss= 0.69782 val_acc= 0.58065 time= 0.23440
Epoch: 0002 train_loss= 0.69839 train_acc= 0.52121 val_loss= 0.69559 val_acc= 0.56452 time= 0.00000
Epoch: 0003 train_loss= 0.69744 train_acc= 0.53030 val_loss= 0.69356 val_acc= 0.56452 time= 0.01562
Epoch: 0004 train_loss= 0.69631 train_acc= 0.52121 val_loss= 0.69183 val_acc= 0.56452 time= 0.00000
Epoch: 0005 train_loss= 0.69452 train_acc= 0.53636 val_loss= 0.69042 val_acc= 0.56452 time= 0.00000
Epoch: 0006 train_loss= 0.69479 train_acc= 0.53636 val_loss= 0.68947 val_acc= 0.56452 time= 0.01563
Epoch: 0007 train_loss= 0.69339 train_acc= 0.53030 val_loss= 0.68878 val_acc= 0.56452 time= 0.00000
Epoch: 0008 train_loss= 0.69457 train_acc= 0.53030 val_loss= 0.68840 val_acc= 0.56452 time= 0.00000
Epoch: 0009 train_loss= 0.69414 train_acc= 0.53636 val_loss= 0.68814 val_acc= 0.56452 time= 0.01563
Epoch: 0010 train_loss= 0.69563 train_acc= 0.53030 val_loss= 0.68803 val_acc= 0.56452 time= 0.00000
Epoch: 0011 train_loss= 0.69136 train_acc= 0.53030 val_loss= 0.68798 val_acc= 0.56452 time= 0.00000
Epoch: 0012 train_loss= 0.69409 train_acc= 0.53030 val_loss= 0.68801 val_acc= 0.56452 time= 0.01563
Epoch: 0013 train_loss= 0.69196 train_acc= 0.53636 val_loss= 0.68809 val_acc= 0.56452 time= 0.00000
Epoch: 0014 train_loss= 0.69261 train_acc= 0.53333 val_loss= 0.68825 val_acc= 0.56452 time= 0.00000
Epoch: 0015 train_loss= 0.69467 train_acc= 0.52727 val_loss= 0.68850 val_acc= 0.56452 time= 0.01563
Epoch: 0016 train_loss= 0.69075 train_acc= 0.53030 val_loss= 0.68857 val_acc= 0.56452 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 0.68704 accuracy= 0.55645 time= 0.00000 
