Merge pull request #816 from EleutherAI/flan-benchmark

[Refactor] Flan benchmark

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_global_facts.yaml

+"dataset_name": "global_facts"
+"description": "The following are multiple choice questions (with answers) about global facts.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_global_facts"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_biology.yaml

+"dataset_name": "high_school_biology"
+"description": "The following are multiple choice questions (with answers) about high school biology.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_biology"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_chemistry.yaml

+"dataset_name": "high_school_chemistry"
+"description": "The following are multiple choice questions (with answers) about high school chemistry.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_chemistry"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_computer_science.yaml

+"dataset_name": "high_school_computer_science"
+"description": "The following are multiple choice questions (with answers) about high school computer science.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_computer_science"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_european_history.yaml

+"dataset_name": "high_school_european_history"
+"description": "The following are multiple choice questions (with answers) about high school european history.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_european_history"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_geography.yaml

+"dataset_name": "high_school_geography"
+"description": "The following are multiple choice questions (with answers) about high school geography.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_geography"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_government_and_politics.yaml

+"dataset_name": "high_school_government_and_politics"
+"description": "The following are multiple choice questions (with answers) about high school government and politics.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_government_and_politics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_macroeconomics.yaml

+"dataset_name": "high_school_macroeconomics"
+"description": "The following are multiple choice questions (with answers) about high school macroeconomics.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_macroeconomics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_mathematics.yaml

+"dataset_name": "high_school_mathematics"
+"description": "The following are multiple choice questions (with answers) about high school mathematics.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_mathematics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_microeconomics.yaml

+"dataset_name": "high_school_microeconomics"
+"description": "The following are multiple choice questions (with answers) about high school microeconomics.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_microeconomics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_physics.yaml

+"dataset_name": "high_school_physics"
+"description": "The following are multiple choice questions (with answers) about high school physics.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_physics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_psychology.yaml

+"dataset_name": "high_school_psychology"
+"description": "The following are multiple choice questions (with answers) about high school psychology.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_psychology"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_statistics.yaml

+"dataset_name": "high_school_statistics"
+"description": "The following are multiple choice questions (with answers) about high school statistics.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_statistics"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_us_history.yaml

+"dataset_name": "high_school_us_history"
+"description": "The following are multiple choice questions (with answers) about high school us history.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_us_history"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_high_school_world_history.yaml

+"dataset_name": "high_school_world_history"
+"description": "The following are multiple choice questions (with answers) about high school world history.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_high_school_world_history"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_human_aging.yaml

+"dataset_name": "human_aging"
+"description": "The following are multiple choice questions (with answers) about human aging.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_human_aging"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_human_sexuality.yaml

+"dataset_name": "human_sexuality"
+"description": "The following are multiple choice questions (with answers) about human sexuality.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_human_sexuality"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_international_law.yaml

+"dataset_name": "international_law"
+"description": "The following are multiple choice questions (with answers) about international law.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_international_law"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_jurisprudence.yaml

+"dataset_name": "jurisprudence"
+"description": "The following are multiple choice questions (with answers) about jurisprudence.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_jurisprudence"

lm_eval/tasks/mmlu/flan_n_shot/mmlu_gen_logical_fallacies.yaml

+"dataset_name": "logical_fallacies"
+"description": "The following are multiple choice questions (with answers) about logical fallacies.\n\n"
+"include": "_mmlu_flan_generative_template_yaml"
+"task": "mmlu_flan_n_shot_generative_logical_fallacies"