Epoch: 0001 train_loss= 1.39403 train_acc= 0.24219 val_loss= 1.39200 val_acc= 0.28333 time= 0.69122
Epoch: 0002 train_loss= 1.39022 train_acc= 0.29688 val_loss= 1.39139 val_acc= 0.30000 time= 0.01627
Epoch: 0003 train_loss= 1.38680 train_acc= 0.29883 val_loss= 1.39188 val_acc= 0.30000 time= 0.01741
Epoch: 0004 train_loss= 1.38382 train_acc= 0.30859 val_loss= 1.39330 val_acc= 0.30000 time= 0.01496
Epoch: 0005 train_loss= 1.38125 train_acc= 0.30859 val_loss= 1.39552 val_acc= 0.30000 time= 0.01699
Epoch: 0006 train_loss= 1.38021 train_acc= 0.30859 val_loss= 1.39817 val_acc= 0.30000 time= 0.01744
Epoch: 0007 train_loss= 1.37916 train_acc= 0.31055 val_loss= 1.40096 val_acc= 0.30000 time= 0.01508
Epoch: 0008 train_loss= 1.37862 train_acc= 0.31445 val_loss= 1.40364 val_acc= 0.30000 time= 0.01611
Epoch: 0009 train_loss= 1.37888 train_acc= 0.30859 val_loss= 1.40585 val_acc= 0.30000 time= 0.01502
Epoch: 0010 train_loss= 1.37806 train_acc= 0.31055 val_loss= 1.40758 val_acc= 0.30000 time= 0.01919
Epoch: 0011 train_loss= 1.37768 train_acc= 0.31055 val_loss= 1.40878 val_acc= 0.30000 time= 0.01545
Epoch: 0012 train_loss= 1.37782 train_acc= 0.30859 val_loss= 1.40940 val_acc= 0.30000 time= 0.01704
Early stopping...
Optimization Finished!
Test set results: cost= 1.38785 accuracy= 0.31667 time= 0.00699 
