Epoch: 0001 train_loss= 2.08722 train_acc= 0.10692 val_loss= 2.08398 val_acc= 0.20690 time= 0.12501
Epoch: 0002 train_loss= 2.08431 train_acc= 0.18239 val_loss= 2.08112 val_acc= 0.20690 time= 0.01562
Epoch: 0003 train_loss= 2.08164 train_acc= 0.18239 val_loss= 2.07851 val_acc= 0.20690 time= 0.00000
Epoch: 0004 train_loss= 2.07882 train_acc= 0.18239 val_loss= 2.07620 val_acc= 0.20690 time= 0.01563
Epoch: 0005 train_loss= 2.07622 train_acc= 0.18239 val_loss= 2.07409 val_acc= 0.20690 time= 0.01562
Epoch: 0006 train_loss= 2.07305 train_acc= 0.18239 val_loss= 2.07245 val_acc= 0.20690 time= 0.00000
Epoch: 0007 train_loss= 2.06982 train_acc= 0.18239 val_loss= 2.07124 val_acc= 0.20690 time= 0.01563
Epoch: 0008 train_loss= 2.06693 train_acc= 0.18239 val_loss= 2.07051 val_acc= 0.20690 time= 0.00000
Epoch: 0009 train_loss= 2.06455 train_acc= 0.18239 val_loss= 2.07036 val_acc= 0.20690 time= 0.01563
Epoch: 0010 train_loss= 2.06042 train_acc= 0.18239 val_loss= 2.07081 val_acc= 0.20690 time= 0.01562
Epoch: 0011 train_loss= 2.05909 train_acc= 0.18239 val_loss= 2.07195 val_acc= 0.20690 time= 0.00000
Epoch: 0012 train_loss= 2.05537 train_acc= 0.18239 val_loss= 2.07387 val_acc= 0.20690 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 2.09157 accuracy= 0.08475 time= 0.00000 
