change back to original dataset path

lm_eval/tasks/bigbench/greedy_until_template_yaml

 group: bigbench
-dataset_path: hails/bigbench
+dataset_path: bigbench # will switch to `hails/bigbench` when all tasks are pushed
 output_type: greedy_until
 dataset_kwargs:
   # num_shots: 0 # TODO: num of shots for `bigbench` HF dataset should be controlled through this, not through the typical methods

lm_eval/tasks/bigbench/multiple_choice_template_yaml

 group: bigbench
-dataset_path: hails/bigbench
+dataset_path: bigbench # will switch to `hails/bigbench` when all tasks are pushed
 dataset_kwargs:
   # num_shots: 0 # TODO: num of shots for `bigbench` HF dataset should be controlled through this, not through the typical methods
   # subtask_name: null