add flan_cot_zeroshot

lm_eval/tasks/bbh/flan_cot_zeroshot/snarks.yaml

+"dataset_name": "snarks"
+"description": "Determine which of two sentences is sarcastic.\n\nAccording to Cambridge University Dictionary, sarcasm is \"the use of remarks that clearly mean the opposite of what they say, made in order to hurt someone's feelings or to criticize something in a humorous way.\" Sarcastic sentences often contain satirical or ironic utterances, hyperboles, ambivalent or witty remarks.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_snarks"

lm_eval/tasks/bbh/flan_cot_zeroshot/sports_understanding.yaml

+"dataset_name": "sports_understanding"
+"description": "Determine whether an artificially constructed sentence relating to sports is plausible or not.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_sports_understanding"

lm_eval/tasks/bbh/flan_cot_zeroshot/temporal_sequences.yaml

+"dataset_name": "temporal_sequences"
+"description": "Task description: Answer questions about which times certain events could have occurred.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_temporal_sequences"

lm_eval/tasks/bbh/flan_cot_zeroshot/tracking_shuffled_objects_five_objects.yaml

+"dataset_name": "tracking_shuffled_objects_five_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_tracking_shuffled_objects_five_objects"

lm_eval/tasks/bbh/flan_cot_zeroshot/tracking_shuffled_objects_seven_objects.yaml

+"dataset_name": "tracking_shuffled_objects_seven_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_tracking_shuffled_objects_seven_objects"

lm_eval/tasks/bbh/flan_cot_zeroshot/tracking_shuffled_objects_three_objects.yaml

+"dataset_name": "tracking_shuffled_objects_three_objects"
+"description": "A task requiring determining the final positions of a set of objects given their initial positions and a description of a sequence of swaps.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_tracking_shuffled_objects_three_objects"

lm_eval/tasks/bbh/flan_cot_zeroshot/web_of_lies.yaml

+"dataset_name": "web_of_lies"
+"description": "Evaluate a random boolean function expressed as a word problem.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_web_of_lies"

lm_eval/tasks/bbh/flan_cot_zeroshot/word_sorting.yaml

+"dataset_name": "word_sorting"
+"description": "Sort a list of words.\n\n"
+"doc_to_text": "Q: {{input}}\nA: Let's think step by step.\n"
+"include": "_template_yaml"
+"task": "bbh_flan_cot_zeroshot_word_sorting"