open-llm-leaderboard-old/details_Sharathhebbar24__chat_gpt2_dpo
收藏数据集概述
数据集摘要
该数据集是在对模型 Sharathhebbar24/chat_gpt2_dpo 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_Sharathhebbar24__chat_gpt2_dpo", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-01-24T23:16:20.806902 的运行： python { "all": { "acc": 0.24915779048270345, "acc_stderr": 0.030509906389610868, "acc_norm": 0.25041231816215265, "acc_norm_stderr": 0.03132600249114931, "mc1": 0.2521419828641371, "mc1_stderr": 0.015201522246299965, "mc2": 0.41257163824244014, "mc2_stderr": 0.015127188811834062 }, "harness|arc:challenge|25": { "acc": 0.18686006825938567, "acc_stderr": 0.011391015649694391, "acc_norm": 0.23976109215017063, "acc_norm_stderr": 0.012476304127453954 }, "harness|hellaswag|10": { "acc": 0.28978291177056364, "acc_stderr": 0.004527343651130803, "acc_norm": 0.3121888070105557, "acc_norm_stderr": 0.0046243936909668975 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3037037037037037, "acc_stderr": 0.039725528847851375, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.039725528847851375 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "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": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.19, "acc_stderr": 0.039427724440366234, "acc_norm": 0.19, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.24561403508771928, "acc_stderr": 0.04049339297748142, "acc_norm": 0.24561403508771928, "acc_norm_stderr": 0.04049339297748142 }, "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": 0.24074074074074073, "acc_stderr": 0.02201908001221789, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.02201908001221789 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1349206349206349, "acc_stderr": 0.030557101589417515, "acc_norm": 0.1349206349206349, "acc_norm_stderr": 0.030557101589417515 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.16, "acc_stderr": 0.03684529491774708, "acc_norm": 0.16, "acc_norm_stderr": 0.03684529491774708 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.1774193548387097, "acc_stderr": 0.02173254068932927, "acc_norm": 0.1774193548387097, "acc_norm_stderr": 0.02173254068932927 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.24630541871921183, "acc_stderr": 0.030315099285617736, "acc_norm": 0.24630541871921183, "acc_norm_stderr": 0.030315099285617736 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542126, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542126 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "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": 0.37305699481865284, "acc_stderr": 0.03490205592048573, "acc_norm": 0.37305699481865284, "acc_norm_stderr": 0.03490205592048573 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.02242127361292371, "acc_norm": 0.26666666666666666, "acc_norm_stderr": 0.02242127361292371 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.21481481481481482, "acc_stderr": 0.025040443877000683, "acc_norm": 0.21481481481481482, "acc_norm_stderr": 0.025040443877000683 }, "harness|hendrycksTest-high_school_microeconom
