Reduce the MMLU evaluation benchmark dataset to the minimum set of features

[markmc]

In #180 we believe that the MMLU evaluation benchmark dataset only needs question, choices and answer features because that is all the lm-eval task will use:

doc_to_text: "{{question.strip()}}\nA. {{choices[0]}}\nB. {{choices[1]}}\nC. {{choices[2]}}\nD. {{choices[3]}}\nAnswer:"
doc_to_choice: ["A", "B", "C", "D"]
doc_to_target: answer

We should update the generator to remove any other features but these, to make the requirements of the evaluation process more clear and to reduce the size of the dataset.