open-llm-leaderboard-old/details_azarafrooz__mistral-v2-7b-selfplay-v0
收藏数据集概述
数据集简介
该数据集是在对模型 azarafrooz/mistral-v2-7b-selfplay-v0 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集由 1 次运行创建，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。
- 额外的 "results" 配置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_azarafrooz__mistral-v2-7b-selfplay-v0", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-13T18:28:50.684897 运行 的最新结果：
python { "all": { "acc": 0.6078421506014341, "acc_stderr": 0.033132054297483685, "acc_norm": 0.6123125611402046, "acc_norm_stderr": 0.033802615872941706, "mc1": 0.5287637698898409, "mc1_stderr": 0.017474513848525518, "mc2": 0.6814091675169902, "mc2_stderr": 0.015207134176475507 }, "harness|arc:challenge|25": { "acc": 0.5887372013651877, "acc_stderr": 0.014379441068522085, "acc_norm": 0.6305460750853242, "acc_norm_stderr": 0.014104578366491888 }, "harness|hellaswag|10": { "acc": 0.6680940051782513, "acc_stderr": 0.0046993506536956225, "acc_norm": 0.8488348934475204, "acc_norm_stderr": 0.003574776594108505 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.042763494943765995, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.042763494943765995 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5895953757225434, "acc_stderr": 0.037507570448955356, "acc_norm": 0.5895953757225434, "acc_norm_stderr": 0.037507570448955356 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5361702127659574, "acc_stderr": 0.032600385118357715, "acc_norm": 0.5361702127659574, "acc_norm_stderr": 0.032600385118357715 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366596, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366596 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6137931034482759, "acc_stderr": 0.04057324734419035, "acc_norm": 0.6137931034482759, "acc_norm_stderr": 0.04057324734419035 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.373015873015873, "acc_stderr": 0.02490699045899257, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.02490699045899257 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.635483870967742, "acc_stderr": 0.027379871229943245, "acc_norm": 0.635483870967742, "acc_norm_stderr": 0.027379871229943245 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7626262626262627, "acc_stderr": 0.030313710538198896, "acc_norm": 0.7626262626262627, "acc_norm_stderr": 0.030313710538198896 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8549222797927462, "acc_stderr": 0.025416343096306443, "acc_norm": 0.8549222797927462, "acc_norm_stderr": 0.025416343096306443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.558974358974359, "acc_stderr": 0.025174048384000745, "acc_norm": 0.558974358974359, "acc_norm_stderr": 0.025174048384000745 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114993, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.028037929969114993 }, "harness|hendrycksTest-high_school_microeconomics|5": {
