open-llm-leaderboard-old/details_azarafrooz__mistral-v2-7b-selfplay-low-tmp
收藏数据集概述
数据集简介
该数据集是在评估模型 azarafrooz/mistral-v2-7b-selfplay-low-tmp 的过程中自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集由1次运行生成，每个运行的结果存储在特定的分割中，分割名称使用运行的时间戳。
- 最新结果："train" 分割始终指向最新的结果。
- 汇总结果：额外配置 "results" 存储所有运行结果的汇总，用于计算和显示在 Open LLM Leaderboard 上的聚合指标。
加载数据示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_azarafrooz__mistral-v2-7b-selfplay-low-tmp", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-21T11:31:23.339994 运行 的最新结果：
python { "all": { "acc": 0.6075157900064023, "acc_stderr": 0.0331399850758573, "acc_norm": 0.6121293596581681, "acc_norm_stderr": 0.03381162626787054, "mc1": 0.5287637698898409, "mc1_stderr": 0.017474513848525518, "mc2": 0.6813244751586996, "mc2_stderr": 0.015204757863568796 }, "harness|arc:challenge|25": { "acc": 0.5861774744027304, "acc_stderr": 0.014392730009221005, "acc_norm": 0.6305460750853242, "acc_norm_stderr": 0.014104578366491888 }, "harness|hellaswag|10": { "acc": 0.6670981876120294, "acc_stderr": 0.004702886273189419, "acc_norm": 0.849133638717387, "acc_norm_stderr": 0.0035718708487317116 }, "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": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "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": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6716981132075471, "acc_stderr": 0.02890159361241178, "acc_norm": 0.6716981132075471, "acc_norm_stderr": 0.02890159361241178 }, "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": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5838150289017341, "acc_stderr": 0.03758517775404948, "acc_norm": 0.5838150289017341, "acc_norm_stderr": 0.03758517775404948 }, "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": 0.5319148936170213, "acc_stderr": 0.03261936918467382, "acc_norm": 0.5319148936170213, "acc_norm_stderr": 0.03261936918467382 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.04615186962583703, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.04615186962583703 }, "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": 0.3783068783068783, "acc_stderr": 0.024976954053155254, "acc_norm": 0.3783068783068783, "acc_norm_stderr": 0.024976954053155254 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04426266681379909, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04426266681379909 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.632258064516129, "acc_stderr": 0.02743086657997347, "acc_norm": 0.632258064516129, "acc_norm_stderr": 0.02743086657997347 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "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": {
