open-llm-leaderboard-old/details_jisukim8873__falcon-7B-case-c
收藏数据集概述
数据集简介
该数据集是在对模型 jisukim8873/falcon-7B-case-c 进行评估运行期间自动创建的,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。
- 创建来源:数据集由1次运行创建,每个运行结果作为特定分片存储在每个配置中,分片名称使用运行的时间戳。
- 最新结果:"train" 分片始终指向最新结果。
- 聚合结果:额外配置 "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_jisukim8873__falcon-7B-case-c", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-07T11:30:30.635454 运行的最新结果:
python { "all": { "acc": 0.29836515196137414, "acc_stderr": 0.032077752137299256, "acc_norm": 0.2990514171098905, "acc_norm_stderr": 0.03281186677025003, "mc1": 0.2668298653610771, "mc1_stderr": 0.01548369193923727, "mc2": 0.3826492372963991, "mc2_stderr": 0.014401921891655947 }, "harness|arc:challenge|25": { "acc": 0.454778156996587, "acc_stderr": 0.014551507060836353, "acc_norm": 0.4854948805460751, "acc_norm_stderr": 0.014605241081370056 }, "harness|hellaswag|10": { "acc": 0.5984863572993427, "acc_stderr": 0.004892026457294713, "acc_norm": 0.7866958773152758, "acc_norm_stderr": 0.004088034745195346 }, "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": 0.2814814814814815, "acc_stderr": 0.03885004245800254, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.03885004245800254 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.24342105263157895, "acc_stderr": 0.034923496688842384, "acc_norm": 0.24342105263157895, "acc_norm_stderr": 0.034923496688842384 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2981132075471698, "acc_stderr": 0.028152837942493854, "acc_norm": 0.2981132075471698, "acc_norm_stderr": 0.028152837942493854 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2708333333333333, "acc_stderr": 0.03716177437566017, "acc_norm": 0.2708333333333333, "acc_norm_stderr": 0.03716177437566017 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.03942772444036624, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036624 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3179190751445087, "acc_stderr": 0.03550683989165582, "acc_norm": 0.3179190751445087, "acc_norm_stderr": 0.03550683989165582 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617749, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617749 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.33, "acc_stderr": 0.04725815626252605, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252605 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.32340425531914896, "acc_stderr": 0.030579442773610334, "acc_norm": 0.32340425531914896, "acc_norm_stderr": 0.030579442773610334 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2719298245614035, "acc_stderr": 0.04185774424022056, "acc_norm": 0.2719298245614035, "acc_norm_stderr": 0.04185774424022056 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2698412698412698, "acc_stderr": 0.02286083830923207, "acc_norm": 0.2698412698412698, "acc_norm_stderr": 0.02286083830923207 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.18253968253968253, "acc_stderr": 0.034550710191021496, "acc_norm": 0.18253968253968253, "acc_norm_stderr": 0.034550710191021496 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.31290322580645163, "acc_stderr": 0.02637756702864586, "acc_norm": 0.31290322580645163, "acc_norm_stderr": 0.02637756702864586 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.29064039408866993, "acc_stderr": 0.03194740072265541, "acc_norm": 0.29064039408866993, "acc_norm_stderr": 0.03194740072265541 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.32727272727272727, "acc_stderr": 0.03663974994391242, "acc_norm": 0.32727272727272727, "acc_norm_stderr": 0.03663974994391242 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.29292929292929293, "acc_stderr": 0.032424979581788166, "acc_norm": 0.29292929292929293, "acc_norm_stderr": 0.032424979581788166 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.31088082901554404, "acc_stderr": 0.03340361906276585, "acc_norm": 0.31088082901554404, "acc_norm_stderr": 0.03340361906276585 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.022421273612923714, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.022421273612923714 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.026



