Commit bbb8386c authored by lintangsutawika's avatar lintangsutawika
Browse files

removed alt worlds prompts

parent 3e5e9da2
"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"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_02_zeroshot_tracking_shuffled_objects_seven_objects"
"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"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_02_zeroshot_tracking_shuffled_objects_three_objects"
"dataset_name": "web_of_lies"
"description": "Evaluate a random boolean function expressed as a word problem.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_02_zeroshot_web_of_lies"
"doc_to_target": target
"doc_to_choice": ["Yes", "No"]
group: bbh_alt_pv_03_zeroshot
dataset_path: lukaemon/bbh
output_type: multiple_choice
test_split: test
doc_to_text: !function ../../styles.styles_03
doc_to_target: !function ../../styles.doc_to_target
doc_to_choice: !function ../../styles.doc_to_choice
num_fewshot: 0
metric_list:
- metric: acc
- metric: acc_norm
- metric: brier_score
"dataset_name": "boolean_expressions"
"description": "Evaluate the result of a random Boolean expression.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_boolean_expressions"
"doc_to_target": target
"doc_to_choice": ["True", "False"]
"dataset_name": "causal_judgement"
"description": "Answer questions about causal attribution.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_causal_judgement"
"dataset_name": "date_understanding"
"description": "Infer the date from context.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_date_understanding"
"dataset_name": "disambiguation_qa"
"description": "Clarify the meaning of sentences with ambiguous pronouns.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_disambiguation_qa"
"dataset_name": "formal_fallacies"
"description": "Distinguish deductively valid arguments from formal fallacies.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_formal_fallacies"
"doc_to_target": target
"doc_to_choice": ["valid", "invalid"]
"dataset_name": "geometric_shapes"
"description": "Name geometric shapes from their SVG paths.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_geometric_shapes"
"dataset_name": "hyperbaton"
"description": "Order adjectives correctly in English sentences.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_hyperbaton"
"dataset_name": "logical_deduction_five_objects"
"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_logical_deduction_five_objects"
"dataset_name": "logical_deduction_seven_objects"
"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_logical_deduction_seven_objects"
"dataset_name": "logical_deduction_three_objects"
"description": "A logical deduction task which requires deducing the order of a sequence of objects.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_logical_deduction_three_objects"
"dataset_name": "movie_recommendation"
"description": "Recommend movies similar to the given list of movies.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_movie_recommendation"
"process_docs": !function ../../utils.fix_movie_recommendation
"dataset_name": "navigate"
"description": "Given a series of navigation instructions, determine whether one would end up back at the starting point.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_navigate"
"dataset_name": "penguins_in_a_table"
"description": "Answer questions about a table of penguins and their attributes.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_penguins_in_a_table"
"dataset_name": "reasoning_about_colored_objects"
"description": "Answer extremely simple questions about the colors of objects on a surface.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_reasoning_about_colored_objects"
"dataset_name": "ruin_names"
"description": "Select the humorous edit that 'ruins' the input movie or musical artist name.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_ruin_names"
"process_docs": !function ../../utils.fix_ruin_names
"dataset_name": "salient_translation_error_detection"
"description": "Detect the type of error in an English translation of a German source sentence.\n\n"
"include": "_zeroshot_template_yaml"
"task": "bbh_alt_pv_03_zeroshot_salient_translation_error_detection"
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment