Merge branch 'main' into longcxt

lm_eval/tasks/llama3/instruct/mmlu/mmlu_human_aging.yaml

+"dataset_name": "human_aging"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_human_aging"
+"task_alias": "human aging"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_human_sexuality.yaml

+"dataset_name": "human_sexuality"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_social_sciences_tasks"
+"task": "mmlu_llama_human_sexuality"
+"task_alias": "human sexuality"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_international_law.yaml

+"dataset_name": "international_law"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_international_law"
+"task_alias": "international law"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_jurisprudence.yaml

+"dataset_name": "jurisprudence"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_jurisprudence"
+"task_alias": "jurisprudence"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_logical_fallacies.yaml

+"dataset_name": "logical_fallacies"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_logical_fallacies"
+"task_alias": "logical fallacies"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_machine_learning.yaml

+"dataset_name": "machine_learning"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_stem_tasks"
+"task": "mmlu_llama_machine_learning"
+"task_alias": "machine learning"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_management.yaml

+"dataset_name": "management"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_management"
+"task_alias": "management"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_marketing.yaml

+"dataset_name": "marketing"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_marketing"
+"task_alias": "marketing"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_medical_genetics.yaml

+"dataset_name": "medical_genetics"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_medical_genetics"
+"task_alias": "medical genetics"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_miscellaneous.yaml

+"dataset_name": "miscellaneous"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_miscellaneous"
+"task_alias": "miscellaneous"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_moral_disputes.yaml

+"dataset_name": "moral_disputes"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_moral_disputes"
+"task_alias": "moral disputes"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_moral_scenarios.yaml

+"dataset_name": "moral_scenarios"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_moral_scenarios"
+"task_alias": "moral scenarios"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_nutrition.yaml

+"dataset_name": "nutrition"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_nutrition"
+"task_alias": "nutrition"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_philosophy.yaml

+"dataset_name": "philosophy"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_philosophy"
+"task_alias": "philosophy"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_prehistory.yaml

+"dataset_name": "prehistory"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_prehistory"
+"task_alias": "prehistory"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_professional_accounting.yaml

+"dataset_name": "professional_accounting"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_professional_accounting"
+"task_alias": "professional accounting"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_professional_law.yaml

+"dataset_name": "professional_law"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_humanities_tasks"
+"task": "mmlu_llama_professional_law"
+"task_alias": "professional law"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_professional_medicine.yaml

+"dataset_name": "professional_medicine"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_other_tasks"
+"task": "mmlu_llama_professional_medicine"
+"task_alias": "professional medicine"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_professional_psychology.yaml

+"dataset_name": "professional_psychology"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_social_sciences_tasks"
+"task": "mmlu_llama_professional_psychology"
+"task_alias": "professional psychology"

lm_eval/tasks/llama3/instruct/mmlu/mmlu_public_relations.yaml

+"dataset_name": "public_relations"
+"include": "_continuation_template_yaml"
+"tag": "mmlu_llama_social_sciences_tasks"
+"task": "mmlu_llama_public_relations"
+"task_alias": "public relations"