Epoch: 0001 train_loss= 2.08244 train_acc= 0.16352 val_loss= 2.08603 val_acc= 0.10345 time= 0.12501
Epoch: 0002 train_loss= 2.08039 train_acc= 0.16352 val_loss= 2.08460 val_acc= 0.10345 time= 0.00000
Epoch: 0003 train_loss= 2.07908 train_acc= 0.16352 val_loss= 2.08333 val_acc= 0.20690 time= 0.01563
Epoch: 0004 train_loss= 2.07635 train_acc= 0.17610 val_loss= 2.08229 val_acc= 0.20690 time= 0.00000
Epoch: 0005 train_loss= 2.07508 train_acc= 0.16352 val_loss= 2.08119 val_acc= 0.20690 time= 0.01563
Epoch: 0006 train_loss= 2.07236 train_acc= 0.16352 val_loss= 2.08021 val_acc= 0.20690 time= 0.01563
Epoch: 0007 train_loss= 2.07131 train_acc= 0.16352 val_loss= 2.07923 val_acc= 0.20690 time= 0.00000
Epoch: 0008 train_loss= 2.06797 train_acc= 0.16352 val_loss= 2.07841 val_acc= 0.20690 time= 0.01562
Epoch: 0009 train_loss= 2.06776 train_acc= 0.16352 val_loss= 2.07770 val_acc= 0.20690 time= 0.00000
Epoch: 0010 train_loss= 2.06325 train_acc= 0.16352 val_loss= 2.07710 val_acc= 0.20690 time= 0.01563
Epoch: 0011 train_loss= 2.06316 train_acc= 0.16352 val_loss= 2.07653 val_acc= 0.20690 time= 0.01624
Epoch: 0012 train_loss= 2.06206 train_acc= 0.16352 val_loss= 2.07611 val_acc= 0.20690 time= 0.01000
Epoch: 0013 train_loss= 2.05922 train_acc= 0.16352 val_loss= 2.07578 val_acc= 0.20690 time= 0.00106
Epoch: 0014 train_loss= 2.05788 train_acc= 0.16352 val_loss= 2.07567 val_acc= 0.20690 time= 0.01562
Epoch: 0015 train_loss= 2.05629 train_acc= 0.16352 val_loss= 2.07572 val_acc= 0.20690 time= 0.00000
Epoch: 0016 train_loss= 2.05546 train_acc= 0.16352 val_loss= 2.07585 val_acc= 0.20690 time= 0.01563
Epoch: 0017 train_loss= 2.05452 train_acc= 0.16352 val_loss= 2.07610 val_acc= 0.20690 time= 0.00000
Epoch: 0018 train_loss= 2.05569 train_acc= 0.16352 val_loss= 2.07631 val_acc= 0.20690 time= 0.01563
Epoch: 0019 train_loss= 2.05486 train_acc= 0.16352 val_loss= 2.07646 val_acc= 0.20690 time= 0.01562
Early stopping...
Optimization Finished!
Test set results: cost= 2.08824 accuracy= 0.11864 time= 0.00000 
