Epoch: 0001 train_loss= 1.39573 train_acc= 0.25781 val_loss= 1.39016 val_acc= 0.23214 time= 0.23439
Epoch: 0002 train_loss= 1.39366 train_acc= 0.25586 val_loss= 1.38897 val_acc= 0.23214 time= 0.01563
Epoch: 0003 train_loss= 1.39232 train_acc= 0.25586 val_loss= 1.38762 val_acc= 0.23214 time= 0.01562
Epoch: 0004 train_loss= 1.39093 train_acc= 0.25586 val_loss= 1.38692 val_acc= 0.23214 time= 0.01563
Epoch: 0005 train_loss= 1.38953 train_acc= 0.25781 val_loss= 1.38633 val_acc= 0.23214 time= 0.01563
Epoch: 0006 train_loss= 1.38859 train_acc= 0.25586 val_loss= 1.38602 val_acc= 0.23214 time= 0.01563
Epoch: 0007 train_loss= 1.38751 train_acc= 0.25586 val_loss= 1.38556 val_acc= 0.23214 time= 0.01563
Epoch: 0008 train_loss= 1.38637 train_acc= 0.25781 val_loss= 1.38501 val_acc= 0.23214 time= 0.01563
Epoch: 0009 train_loss= 1.38519 train_acc= 0.25781 val_loss= 1.38440 val_acc= 0.23214 time= 0.01563
Epoch: 0010 train_loss= 1.38371 train_acc= 0.25781 val_loss= 1.38373 val_acc= 0.23214 time= 0.01563
Epoch: 0011 train_loss= 1.38294 train_acc= 0.25195 val_loss= 1.38305 val_acc= 0.39286 time= 0.01563
Epoch: 0012 train_loss= 1.38116 train_acc= 0.29102 val_loss= 1.38240 val_acc= 0.39286 time= 0.01563
Epoch: 0013 train_loss= 1.37935 train_acc= 0.30469 val_loss= 1.38181 val_acc= 0.39286 time= 0.01563
Epoch: 0014 train_loss= 1.37812 train_acc= 0.30078 val_loss= 1.38134 val_acc= 0.39286 time= 0.03125
Epoch: 0015 train_loss= 1.37688 train_acc= 0.30078 val_loss= 1.38103 val_acc= 0.39286 time= 0.01563
Epoch: 0016 train_loss= 1.37578 train_acc= 0.30078 val_loss= 1.38095 val_acc= 0.39286 time= 0.01563
Epoch: 0017 train_loss= 1.37452 train_acc= 0.30078 val_loss= 1.38118 val_acc= 0.39286 time= 0.01563
Epoch: 0018 train_loss= 1.37294 train_acc= 0.30078 val_loss= 1.38174 val_acc= 0.39286 time= 0.01563
Epoch: 0019 train_loss= 1.37324 train_acc= 0.30078 val_loss= 1.38272 val_acc= 0.39286 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 1.36939 accuracy= 0.29204 time= 0.00000 
