Epoch: 0001 train_loss= 1.38946 train_acc= 0.35831 val_loss= 1.38236 val_acc= 0.42857 time= 0.15626
Epoch: 0002 train_loss= 1.38709 train_acc= 0.35831 val_loss= 1.37990 val_acc= 0.42857 time= 0.01563
Epoch: 0003 train_loss= 1.38522 train_acc= 0.35505 val_loss= 1.37735 val_acc= 0.42857 time= 0.01562
Epoch: 0004 train_loss= 1.38293 train_acc= 0.35831 val_loss= 1.37483 val_acc= 0.42857 time= 0.00000
Epoch: 0005 train_loss= 1.38082 train_acc= 0.35831 val_loss= 1.37234 val_acc= 0.42857 time= 0.01563
Epoch: 0006 train_loss= 1.37863 train_acc= 0.35831 val_loss= 1.36995 val_acc= 0.42857 time= 0.01563
Epoch: 0007 train_loss= 1.37650 train_acc= 0.35831 val_loss= 1.36771 val_acc= 0.42857 time= 0.01563
Epoch: 0008 train_loss= 1.37361 train_acc= 0.35831 val_loss= 1.36560 val_acc= 0.42857 time= 0.01563
Epoch: 0009 train_loss= 1.37153 train_acc= 0.35831 val_loss= 1.36372 val_acc= 0.42857 time= 0.01563
Epoch: 0010 train_loss= 1.36964 train_acc= 0.35831 val_loss= 1.36203 val_acc= 0.42857 time= 0.00000
Epoch: 0011 train_loss= 1.36575 train_acc= 0.35831 val_loss= 1.36052 val_acc= 0.42857 time= 0.01563
Epoch: 0012 train_loss= 1.36433 train_acc= 0.35831 val_loss= 1.35932 val_acc= 0.42857 time= 0.01563
Epoch: 0013 train_loss= 1.36174 train_acc= 0.35831 val_loss= 1.35820 val_acc= 0.42857 time= 0.01563
Epoch: 0014 train_loss= 1.35942 train_acc= 0.35831 val_loss= 1.35745 val_acc= 0.42857 time= 0.01563
Epoch: 0015 train_loss= 1.35918 train_acc= 0.35831 val_loss= 1.35713 val_acc= 0.42857 time= 0.01563
Epoch: 0016 train_loss= 1.35785 train_acc= 0.35831 val_loss= 1.35731 val_acc= 0.42857 time= 0.00000
Epoch: 0017 train_loss= 1.35716 train_acc= 0.35505 val_loss= 1.35795 val_acc= 0.42857 time= 0.01563
Epoch: 0018 train_loss= 1.35601 train_acc= 0.35831 val_loss= 1.35897 val_acc= 0.42857 time= 0.01562
Epoch: 0019 train_loss= 1.35660 train_acc= 0.35831 val_loss= 1.36033 val_acc= 0.42857 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.41411 accuracy= 0.28319 time= 0.00000 
