Epoch: 0001 train_loss= 1.39201 train_acc= 0.30168 val_loss= 1.39626 val_acc= 0.23214 time= 0.84381
Epoch: 0002 train_loss= 1.39116 train_acc= 0.29888 val_loss= 1.39468 val_acc= 0.23214 time= 0.00000
Epoch: 0003 train_loss= 1.38999 train_acc= 0.29330 val_loss= 1.39320 val_acc= 0.23214 time= 0.01563
Epoch: 0004 train_loss= 1.38869 train_acc= 0.29888 val_loss= 1.39183 val_acc= 0.23214 time= 0.00000
Epoch: 0005 train_loss= 1.38586 train_acc= 0.28911 val_loss= 1.39065 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.38527 train_acc= 0.29888 val_loss= 1.38962 val_acc= 0.23214 time= 0.00000
Epoch: 0007 train_loss= 1.38239 train_acc= 0.30866 val_loss= 1.38873 val_acc= 0.25000 time= 0.01563
Epoch: 0008 train_loss= 1.38184 train_acc= 0.30168 val_loss= 1.38801 val_acc= 0.25000 time= 0.00000
Epoch: 0009 train_loss= 1.38158 train_acc= 0.28073 val_loss= 1.38747 val_acc= 0.23214 time= 0.01563
Epoch: 0010 train_loss= 1.38102 train_acc= 0.28631 val_loss= 1.38717 val_acc= 0.23214 time= 0.00000
Epoch: 0011 train_loss= 1.37942 train_acc= 0.29190 val_loss= 1.38712 val_acc= 0.21429 time= 0.01563
Epoch: 0012 train_loss= 1.37940 train_acc= 0.27793 val_loss= 1.38725 val_acc= 0.23214 time= 0.00000
Epoch: 0013 train_loss= 1.37889 train_acc= 0.28073 val_loss= 1.38750 val_acc= 0.23214 time= 0.00000
Epoch: 0014 train_loss= 1.37921 train_acc= 0.28771 val_loss= 1.38787 val_acc= 0.23214 time= 0.01563
Epoch: 0015 train_loss= 1.37782 train_acc= 0.30307 val_loss= 1.38821 val_acc= 0.23214 time= 0.00000
Early stopping...
Optimization Finished!
Test set results: cost= 1.37817 accuracy= 0.30973 time= 0.01563 
