Epoch: 0001 train_loss= 2.08072 train_acc= 0.14825 val_loss= 2.08650 val_acc= 0.20690 time= 0.82818
Epoch: 0002 train_loss= 2.07660 train_acc= 0.14825 val_loss= 2.08548 val_acc= 0.20690 time= 0.01563
Epoch: 0003 train_loss= 2.07525 train_acc= 0.14825 val_loss= 2.08457 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.07409 train_acc= 0.14825 val_loss= 2.08400 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.07061 train_acc= 0.14825 val_loss= 2.08375 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.06904 train_acc= 0.14825 val_loss= 2.08405 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.06476 train_acc= 0.14825 val_loss= 2.08485 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.06284 train_acc= 0.14825 val_loss= 2.08614 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.06312 train_acc= 0.14825 val_loss= 2.08800 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.06174 train_acc= 0.14825 val_loss= 2.09044 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.05867 train_acc= 0.14825 val_loss= 2.09339 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.05677 train_acc= 0.15364 val_loss= 2.09687 val_acc= 0.20690 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 2.04039 accuracy= 0.18644 time= 0.01563 
