Epoch: 0001 train_loss= 2.09000 train_acc= 0.18868 val_loss= 2.08065 val_acc= 0.13793 time= 0.32934
Epoch: 0002 train_loss= 2.07997 train_acc= 0.11321 val_loss= 2.07279 val_acc= 0.13793 time= 0.00107
Epoch: 0003 train_loss= 2.04337 train_acc= 0.16981 val_loss= 2.07156 val_acc= 0.13793 time= 0.01562
Epoch: 0004 train_loss= 2.04754 train_acc= 0.16981 val_loss= 2.07422 val_acc= 0.17241 time= 0.01563
Epoch: 0005 train_loss= 2.03080 train_acc= 0.22013 val_loss= 2.07280 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.03115 train_acc= 0.20755 val_loss= 2.07588 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.01439 train_acc= 0.15094 val_loss= 2.08033 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.02797 train_acc= 0.17610 val_loss= 2.08450 val_acc= 0.20690 time= 0.01563
Epoch: 0009 train_loss= 2.01501 train_acc= 0.20126 val_loss= 2.08902 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.00906 train_acc= 0.16981 val_loss= 2.09243 val_acc= 0.17241 time= 0.01563
Epoch: 0011 train_loss= 2.00188 train_acc= 0.23270 val_loss= 2.09375 val_acc= 0.17241 time= 0.01563
Epoch: 0012 train_loss= 2.04448 train_acc= 0.21384 val_loss= 2.08987 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.25293 accuracy= 0.03390 time= 0.00000 
