push updated bigbench task yamls

lm_eval/tasks/bigbench/multiple_choice/geometric_shapes.yaml

 # Generated by utils.py
-dataset_name: geometric_shapes
+dataset_name: geometric_shapes_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_geometric_shapes_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/goal_step_wikihow.yaml

 # Generated by utils.py
-dataset_name: goal_step_wikihow
+dataset_name: goal_step_wikihow_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_goal_step_wikihow_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/gre_reading_comprehension.yaml

 # Generated by utils.py
-dataset_name: gre_reading_comprehension
+dataset_name: gre_reading_comprehension_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_gre_reading_comprehension_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hhh_alignment.yaml

 # Generated by utils.py
-dataset_name: hhh_alignment
+dataset_name: hhh_alignment_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_hhh_alignment_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hindi_question_answering.yaml

 # Generated by utils.py
-dataset_name: hindi_question_answering
+dataset_name: hindi_question_answering_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_hindi_question_answering_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hindu_knowledge.yaml

 # Generated by utils.py
-dataset_name: hindu_knowledge
+dataset_name: hindu_knowledge_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_hindu_knowledge_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hinglish_toxicity.yaml

 # Generated by utils.py
-dataset_name: hinglish_toxicity
+dataset_name: hinglish_toxicity_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_hinglish_toxicity_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/human_organs_senses.yaml

 # Generated by utils.py
-dataset_name: human_organs_senses
+dataset_name: human_organs_senses_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_human_organs_senses_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/hyperbaton.yaml

 # Generated by utils.py
-dataset_name: hyperbaton
+dataset_name: hyperbaton_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_hyperbaton_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/identify_math_theorems.yaml

 # Generated by utils.py
-dataset_name: identify_math_theorems
+dataset_name: identify_math_theorems_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_identify_math_theorems_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/identify_odd_metaphor.yaml

 # Generated by utils.py
-dataset_name: identify_odd_metaphor
+dataset_name: identify_odd_metaphor_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_identify_odd_metaphor_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/implicatures.yaml

 # Generated by utils.py
-dataset_name: implicatures
+dataset_name: implicatures_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_implicatures_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/implicit_relations.yaml

 # Generated by utils.py
-dataset_name: implicit_relations
+dataset_name: implicit_relations_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_implicit_relations_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/intent_recognition.yaml

 # Generated by utils.py
-dataset_name: intent_recognition
+dataset_name: intent_recognition_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_intent_recognition_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_nli.yaml

 # Generated by utils.py
-dataset_name: international_phonetic_alphabet_nli
+dataset_name: international_phonetic_alphabet_nli_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_international_phonetic_alphabet_nli_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/international_phonetic_alphabet_transliterate.yaml

 # Generated by utils.py
-dataset_name: international_phonetic_alphabet_transliterate
+dataset_name: international_phonetic_alphabet_transliterate_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_international_phonetic_alphabet_transliterate_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/intersect_geometry.yaml

 # Generated by utils.py
-dataset_name: intersect_geometry
+dataset_name: intersect_geometry_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_intersect_geometry_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/irony_identification.yaml

 # Generated by utils.py
-dataset_name: irony_identification
+dataset_name: irony_identification_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_irony_identification_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/kanji_ascii.yaml

 # Generated by utils.py
-dataset_name: kanji_ascii
+dataset_name: kanji_ascii_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_kanji_ascii_multiple_choice

lm_eval/tasks/bigbench/multiple_choice/kannada.yaml

 # Generated by utils.py
-dataset_name: kannada
+dataset_name: kannada_zero_shot
 include: ../multiple_choice_template_yaml
 task: bigbench_kannada_multiple_choice