open-llm-leaderboard-old/details_vikash06__mistral_v1
收藏数据集概述
数据集简介
该数据集是在模型 vikash06/mistral_v1 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集从 1 次运行中创建。每个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。
- 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 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_vikash06__mistral_v1", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-29T16:14:27.523091 运行的最新结果：
python { "all": { "acc": 0.482622222971472, "acc_stderr": 0.03446310575192786, "acc_norm": 0.48972529162413775, "acc_norm_stderr": 0.035262889522806366, "mc1": 0.23990208078335373, "mc1_stderr": 0.014948812679062133, "mc2": 0.37533793465077725, "mc2_stderr": 0.015845652826796154 }, "harness|arc:challenge|25": { "acc": 0.44283276450511944, "acc_stderr": 0.014515573873348897, "acc_norm": 0.47013651877133106, "acc_norm_stderr": 0.0145853058400071 }, "harness|hellaswag|10": { "acc": 0.5064728141804421, "acc_stderr": 0.004989363276955251, "acc_norm": 0.6757618004381597, "acc_norm_stderr": 0.004671328673217803 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750575, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4342105263157895, "acc_stderr": 0.04033565667848319, "acc_norm": 0.4342105263157895, "acc_norm_stderr": 0.04033565667848319 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5094339622641509, "acc_stderr": 0.030767394707808093, "acc_norm": 0.5094339622641509, "acc_norm_stderr": 0.030767394707808093 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5, "acc_stderr": 0.04181210050035455, "acc_norm": 0.5, "acc_norm_stderr": 0.04181210050035455 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.41040462427745666, "acc_stderr": 0.03750757044895537, "acc_norm": 0.41040462427745666, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.27450980392156865, "acc_stderr": 0.04440521906179328, "acc_norm": 0.27450980392156865, "acc_norm_stderr": 0.04440521906179328 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.40425531914893614, "acc_stderr": 0.03208115750788684, "acc_norm": 0.40425531914893614, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374767, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374767 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.45517241379310347, "acc_stderr": 0.04149886942192117, "acc_norm": 0.45517241379310347, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.35714285714285715, "acc_stderr": 0.02467786284133278, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.02467786284133278 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.532258064516129, "acc_stderr": 0.028384747788813336, "acc_norm": 0.532258064516129, "acc_norm_stderr": 0.028384747788813336 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3399014778325123, "acc_stderr": 0.033327690684107895, "acc_norm": 0.3399014778325123, "acc_norm_stderr": 0.033327690684107895 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6060606060606061, "acc_stderr": 0.0381549430868893, "acc_norm": 0.6060606060606061, "acc_norm_stderr": 0.0381549430868893 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5858585858585859, "acc_stderr": 0.03509438348879629, "acc_norm": 0.5858585858585859, "acc_norm_stderr": 0.03509438348879629 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7305699481865285, "acc_stderr": 0.032018671228777947, "acc_norm": 0.7305699481865285, "acc_norm_stderr": 0.032018671228777947 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4717948717948718, "acc_stderr": 0.025310639254933893, "acc_norm": 0.4717948717948718, "acc_norm_stderr": 0.025310639254933893 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.02742001935094526, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.02742001935094526 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.4663865546
