open-llm-leaderboard-old/details_Locutusque__LocutusqueXFelladrin-TinyMistral248M-Instruct
收藏数据集概述
数据集来源
该数据集是在对模型 Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct 进行评估时自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集组成
数据集由 63 个配置组成，每个配置对应一个评估任务。数据集是从 1 次运行中创建的，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。
结果汇总
一个额外的配置 "results" 存储了所有运行的汇总结果，用于计算和显示 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_Locutusque__LocutusqueXFelladrin-TinyMistral248M-Instruct", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-16T13:05:29.280274 运行的最新结果： python { "all": { "acc": 0.2598863864332701, "acc_stderr": 0.03085871471372819, "acc_norm": 0.2612223474549382, "acc_norm_stderr": 0.03168256031998437, "mc1": 0.204406364749082, "mc1_stderr": 0.014117174337432621, "mc2": 0.40124313581017795, "mc2_stderr": 0.01490869512458324 }, "harness|arc:challenge|25": { "acc": 0.19965870307167236, "acc_stderr": 0.011681625756888676, "acc_norm": 0.24744027303754265, "acc_norm_stderr": 0.01261035266329267 }, "harness|hellaswag|10": { "acc": 0.2757418840868353, "acc_stderr": 0.004459740315490862, "acc_norm": 0.2779326827325234, "acc_norm_stderr": 0.004470644845242891 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.1925925925925926, "acc_stderr": 0.03406542058502652, "acc_norm": 0.1925925925925926, "acc_norm_stderr": 0.03406542058502652 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.2236842105263158, "acc_stderr": 0.03391160934343604, "acc_norm": 0.2236842105263158, "acc_norm_stderr": 0.03391160934343604 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.2792452830188679, "acc_stderr": 0.02761116340239972, "acc_norm": 0.2792452830188679, "acc_norm_stderr": 0.02761116340239972 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.26011560693641617, "acc_stderr": 0.033450369167889904, "acc_norm": 0.26011560693641617, "acc_norm_stderr": 0.033450369167889904 }, "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": 0.18, "acc_stderr": 0.03861229196653695, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653695 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3148936170212766, "acc_stderr": 0.030363582197238167, "acc_norm": 0.3148936170212766, "acc_norm_stderr": 0.030363582197238167 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.32456140350877194, "acc_stderr": 0.04404556157374768, "acc_norm": 0.32456140350877194, "acc_norm_stderr": 0.04404556157374768 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135303, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135303 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2724867724867725, "acc_stderr": 0.022930973071633345, "acc_norm": 0.2724867724867725, "acc_norm_stderr": 0.022930973071633345 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23809523809523808, "acc_stderr": 0.03809523809523812, "acc_norm": 0.23809523809523808, "acc_norm_stderr": 0.03809523809523812 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.24193548387096775, "acc_stderr": 0.02436259969303109, "acc_norm": 0.24193548387096775, "acc_norm_stderr": 0.02436259969303109 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2857142857142857, "acc_stderr": 0.031785297106427496, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.031785297106427496 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.032250781083062896, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.032250781083062896 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.37373737373737376, "acc_stderr": 0.034468977386593325, "acc_norm": 0.37373737373737376, "acc_norm_stderr": 0.034468977386593325 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.3626943005181347, "acc_stderr": 0.034697137917043715, "acc_norm": 0.3626943005181347, "acc_norm_stderr": 0.034697137917043715 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.33589743589743587, "acc_stderr": 0.023946724741563976, "acc_norm": 0.33589743589743587, "acc_norm_stderr": 0.023946724741563976 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.25925925925925
