added rte

lm_eval/tasks/super_glue/rte/default.yaml

+group:
+  - super-glue-lm-eval-v1
+task: rte
+dataset_path: super_glue
+dataset_name: rte
+output_type: multiple_choice
+training_split: train
+validation_split: validation
+doc_to_text: "{{sentence1}}\nQuestion: {{sentence2}} True or False?\nAnswer:"
+doc_to_target: label
+doc_to_choice: ['True', 'False']
+metric_list:
+  - metric: acc