MTBenchEvaluator and MMLUEvaluator should be/have static methods

[JamesKunstle]

Evaluator objects shouldn't be reused- once we've evaluated a checkpoint or model, we want to save the score and move on to the next. This motivates a reasonable design change, implementing something like:

class MMLUEvaluator(Evaluator):

    def __init__(self):
        # optional empty initialization 
        ...

    def run(self):
       ...

    @staticmethod
    def run(self, model, tasks, few_shot, batch):
        ...

[nathan-weinberg]

@JamesKunstle if we're outputting the evaluation results and saving it to a file or variable in memory, why not reuse the evaluator class?

[alinaryan]

@JamesKunstle do you have a PR for this already?