Epoch: 0001 train_loss= 2.08340 train_acc= 0.19623 val_loss= 2.08573 val_acc= 0.10345 time= 0.34413
Epoch: 0002 train_loss= 2.08030 train_acc= 0.20000 val_loss= 2.08578 val_acc= 0.10345 time= 0.01562
Epoch: 0003 train_loss= 2.07710 train_acc= 0.20000 val_loss= 2.08600 val_acc= 0.10345 time= 0.00000
Epoch: 0004 train_loss= 2.07322 train_acc= 0.20000 val_loss= 2.08639 val_acc= 0.10345 time= 0.01563
Epoch: 0005 train_loss= 2.07131 train_acc= 0.20000 val_loss= 2.08699 val_acc= 0.10345 time= 0.00000
Epoch: 0006 train_loss= 2.06802 train_acc= 0.20000 val_loss= 2.08774 val_acc= 0.10345 time= 0.01563
Epoch: 0007 train_loss= 2.06485 train_acc= 0.20000 val_loss= 2.08877 val_acc= 0.10345 time= 0.00000
Epoch: 0008 train_loss= 2.05991 train_acc= 0.19623 val_loss= 2.09011 val_acc= 0.10345 time= 0.01563
Epoch: 0009 train_loss= 2.05727 train_acc= 0.20000 val_loss= 2.09188 val_acc= 0.10345 time= 0.00000
Epoch: 0010 train_loss= 2.05389 train_acc= 0.20000 val_loss= 2.09414 val_acc= 0.10345 time= 0.01562
Epoch: 0011 train_loss= 2.05082 train_acc= 0.20000 val_loss= 2.09690 val_acc= 0.10345 time= 0.00000
Epoch: 0012 train_loss= 2.04690 train_acc= 0.20000 val_loss= 2.10027 val_acc= 0.10345 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.10736 accuracy= 0.10169 time= 0.00000 
