open-llm-leaderboard-old/details_Josephgflowers__distillgpt2Cinder
收藏数据集概述
数据集名为 "Evaluation run of Josephgflowers/distillgpt2Cinder"，是在评估模型 Josephgflowers/distillgpt2Cinder 在 Open LLM Leaderboard 上的运行时自动创建的。
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。数据集从 1 次运行中创建，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。
额外配置
一个额外的配置 "results" 存储了所有运行的聚合结果，用于计算和显示在 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_Josephgflowers__distillgpt2Cinder", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-04T23:46:27.372796 运行的最新结果：
python { "all": { "acc": 0.24948426094911816, "acc_stderr": 0.03052443478922094, "acc_norm": 0.2500035098132215, "acc_norm_stderr": 0.031309813832633156, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.43961123482428127, "mc2_stderr": 0.01535210261478119 }, "harness|arc:challenge|25": { "acc": 0.21075085324232082, "acc_stderr": 0.01191827175485218, "acc_norm": 0.24488054607508533, "acc_norm_stderr": 0.012566273985131356 }, "harness|hellaswag|10": { "acc": 0.2713602867954591, "acc_stderr": 0.004437527732850682, "acc_norm": 0.27235610436168095, "acc_norm_stderr": 0.004442623590846321 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.21710526315789475, "acc_stderr": 0.033550453048829226, "acc_norm": 0.21710526315789475, "acc_norm_stderr": 0.033550453048829226 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.23018867924528302, "acc_stderr": 0.025907897122408173, "acc_norm": 0.23018867924528302, "acc_norm_stderr": 0.025907897122408173 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2638888888888889, "acc_stderr": 0.03685651095897532, "acc_norm": 0.2638888888888889, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.16, "acc_stderr": 0.036845294917747094, "acc_norm": 0.16, "acc_norm_stderr": 0.036845294917747094 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2658959537572254, "acc_stderr": 0.03368762932259431, "acc_norm": 0.2658959537572254, "acc_norm_stderr": 0.03368762932259431 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617746, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617746 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.32, "acc_stderr": 0.04688261722621503, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621503 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.20425531914893616, "acc_stderr": 0.026355158413349424, "acc_norm": 0.20425531914893616, "acc_norm_stderr": 0.026355158413349424 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748141, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748141 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2620689655172414, "acc_stderr": 0.036646663372252565, "acc_norm": 0.2620689655172414, "acc_norm_stderr": 0.036646663372252565 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2804232804232804, "acc_stderr": 0.023135287974325635, "acc_norm": 0.2804232804232804, "acc_norm_stderr": 0.023135287974325635 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.14285714285714285, "acc_stderr": 0.03129843185743808, "acc_norm": 0.14285714285714285, "acc_norm_stderr": 0.03129843185743808 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2709677419354839, "acc_stderr": 0.02528441611490016, "acc_norm": 0.2709677419354839, "acc_norm_stderr": 0.02528441611490016 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2955665024630542, "acc_stderr": 0.032104944337514575, "acc_norm": 0.2955665024630542, "acc_norm_stderr": 0.032104944337514575 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.32, "acc_stderr": 0.04688261722621505, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.22424242424242424, "acc_stderr": 0.03256866661681102, "acc_norm": 0.22424242424242424, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3282828282828283, "acc_stderr": 0.03345678422756776, "acc_norm": 0.3282828282828283, "acc_norm_stderr": 0.03345678422756776 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22279792746113988, "acc_stderr": 0.03003114797764154, "acc_norm": 0.22279792746113988, "acc_norm_stderr": 0.03003114797764154 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2153846153846154, "acc_stderr": 0.020843034557462878, "acc_norm": 0.2153846153846154, "acc_norm_stderr": 0.020843034557462878 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962424325073838, "acc_norm": 0.2666666
