add alt prompts for truthfulqa

lm_eval/tasks/truthfulqa/alternative_worlds/prompt_variation/style_01/truthfulqa_mc1.yaml

+task: truthfulqa_mc1_alt_pv_01
+dataset_path: truthful_qa
+dataset_name: multiple_choice
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: null
+num_fewshot: 0
+doc_to_text: "{{question}}"
+doc_to_target: 0
+doc_to_choice: "{{mc1_targets.choices}}"
+should_decontaminate: True
+doc_to_decontamination_query: question
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/truthfulqa/alternative_worlds/prompt_variation/style_01/truthfulqa_mc2.yaml

+include: truthfulqa_mc1.yaml
+task: truthfulqa_mc2_alt_pv_01
+doc_to_target: 0
+doc_to_choice: "{{mc2_targets.choices}}"
+process_results: !function ../../../utils.process_results_mc2
+should_decontaminate: True
+doc_to_decontamination_query: question
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/truthfulqa/alternative_worlds/prompt_variation/style_02/truthfulqa_mc1.yaml

+task: truthfulqa_mc1_alt_pv_02
+dataset_path: truthful_qa
+dataset_name: multiple_choice
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: null
+num_fewshot: 0
+doc_to_choice: "Q: {{mc2_targets.choices}}\nA:"
+doc_to_target: 0
+doc_to_choice: "{{mc1_targets.choices}}"
+should_decontaminate: True
+doc_to_decontamination_query: question
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/truthfulqa/alternative_worlds/prompt_variation/style_02/truthfulqa_mc2.yaml

+include: truthfulqa_mc1.yaml
+task: truthfulqa_mc2_alt_pv_02
+doc_to_target: 0
+doc_to_choice: "{{mc2_targets.choices}}"
+process_results: !function ../../../utils.process_results_mc2
+should_decontaminate: True
+doc_to_decontamination_query: question
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/truthfulqa/alternative_worlds/prompt_variation/style_03/truthfulqa_mc1.yaml

+task: truthfulqa_mc1_alt_pv_03
+dataset_path: truthful_qa
+dataset_name: multiple_choice
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: null
+num_fewshot: 0
+doc_to_choice: "Question: {{mc2_targets.choices}}\nAnswer:"
+doc_to_target: 0
+doc_to_choice: "{{mc1_targets.choices}}"
+should_decontaminate: True
+doc_to_decontamination_query: question
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true

lm_eval/tasks/truthfulqa/alternative_worlds/prompt_variation/style_03/truthfulqa_mc2.yaml

+include: truthfulqa_mc1.yaml
+task: truthfulqa_mc2_alt_pv_03
+doc_to_target: 0
+doc_to_choice: "{{mc2_targets.choices}}"
+process_results: !function ../../../utils.process_results_mc2
+should_decontaminate: True
+doc_to_decontamination_query: question
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true