open-llm-leaderboard-old/details_dotvignesh__perry-7b
收藏数据集概述
该数据集是在评估模型 dotvignesh/perry-7b 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 64 个配置,每个配置对应一个评估任务。
数据集结构
数据集由 2 次运行创建,每次运行可以在每个配置中找到特定的分割,分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。
额外配置
一个额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
数据加载示例
以下是加载特定运行详细信息的示例代码:
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_dotvignesh__perry-7b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-10-23T10:51:37.935635 运行 的最新结果:
python { "all": { "em": 0.0008389261744966443, "em_stderr": 0.0002964962989801269, "f1": 0.05790478187919471, "f1_stderr": 0.0013248182101283533, "acc": 0.41422192675444136, "acc_stderr": 0.0104604764963125 }, "harness|drop|3": { "em": 0.0008389261744966443, "em_stderr": 0.0002964962989801269, "f1": 0.05790478187919471, "f1_stderr": 0.0013248182101283533 }, "harness|gsm8k|5": { "acc": 0.10310841546626232, "acc_stderr": 0.008376436987507811 }, "harness|winogrande|5": { "acc": 0.7253354380426204, "acc_stderr": 0.012544516005117188 } }
配置详情
数据集包含以下配置:
harness_arc_challenge_25harness_drop_3harness_gsm8k_5harness_hellaswag_10harness_hendrycksTest_5harness_hendrycksTest_abstract_algebra_5harness_hendrycksTest_anatomy_5harness_hendrycksTest_astronomy_5harness_hendrycksTest_business_ethics_5harness_hendrycksTest_clinical_knowledge_5harness_hendrycksTest_college_biology_5harness_hendrycksTest_college_chemistry_5harness_hendrycksTest_college_computer_science_5harness_hendrycksTest_college_mathematics_5harness_hendrycksTest_college_medicine_5harness_hendrycksTest_college_physics_5harness_hendrycksTest_computer_security_5harness_hendrycksTest_conceptual_physics_5harness_hendrycksTest_econometrics_5harness_hendrycksTest_electrical_engineering_5harness_hendrycksTest_elementary_mathematics_5harness_hendrycksTest_formal_logic_5harness_hendrycksTest_global_facts_5harness_hendrycksTest_high_school_biology_5harness_hendrycksTest_high_school_chemistry_5harness_hendrycksTest_high_school_computer_science_5harness_hendrycksTest_high_school_european_history_5harness_hendrycksTest_high_school_geography_5harness_hendrycksTest_high_school_government_and_politics_5harness_hendrycksTest_high_school_macroeconomics_5harness_hendrycksTest_high_school_mathematics_5harness_hendrycksTest_high_school_microeconomics_5harness_hendrycksTest_high_school_physics_5harness_hendrycksTest_high_school_psychology_5harness_hendrycksTest_high_school_statistics_5harness_hendrycksTest_high_school_us_history_5harness_hendrycksTest_high_school_world_history_5harness_hendrycksTest_human_aging_5harness_hendrycksTest_human_sexuality_5harness_hendrycksTest_international_law_5harness_hendrycksTest_jurisprudence_5harness_hendrycksTest_logical_fallacies_5harness_hendrycksTest_machine_learning_5harness_hendrycksTest_management_5harness_hendrycksTest_marketing_5harness_hendrycksTest_medical_genetics_5harness_hendrycksTest_miscellaneous_5harness_hendrycksTest_moral_disputes_5harness_hendrycksTest_moral_scenarios_5harness_hendrycksTest_nutrition_5harness_hendrycksTest_philosophy_5harness_hendrycksTest_prehistory_5harness_hendrycksTest_professional_accounting_5harness_hendrycksTest_professional_law_5harness_hendrycksTest_professional_medicine_5harness_hendrycksTest_professional_psychology_5harness_hendrycksTest_public_relations_5harness_hendrycksTest_security_studies_5harness_hendrycksTest_sociology_5harness_hendrycksTest_us_foreign_policy_5harness_hendrycksTest_virology_5harness_hendrycksTest_world_religions_5



