open-llm-leaderboard-old/details_kodonho__Momo-70b-DPO-mixed
收藏数据集概述
数据集简介
该数据集是在模型 kodonho/Momo-70b-DPO-mixed 的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。
- 数据来源：数据集从1次运行中创建，每个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。
- 最新结果："train" 分割总是指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_kodonho__Momo-70b-DPO-mixed", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-18T12:09:45.590059 运行 的最新结果：
python { "all": { "acc": 0.2318376299932094, "acc_stderr": 0.02998135076289475, "acc_norm": 0.23146455622350848, "acc_norm_stderr": 0.03077051926756787, "mc1": 0.2350061199510404, "mc1_stderr": 0.014843061507731603, "mc2": 0.48846362378663954, "mc2_stderr": 0.016303812688575184 }, "harness|arc:challenge|25": { "acc": 0.2235494880546075, "acc_stderr": 0.012174896631202609, "acc_norm": 0.2627986348122867, "acc_norm_stderr": 0.012862523175351335 }, "harness|hellaswag|10": { "acc": 0.2577175861382195, "acc_stderr": 0.004364838000335622, "acc_norm": 0.24975104560844452, "acc_norm_stderr": 0.004319842107724391 }, "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": 0.22962962962962963, "acc_stderr": 0.0363338441407346, "acc_norm": 0.22962962962962963, "acc_norm_stderr": 0.0363338441407346 }, "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": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22641509433962265, "acc_stderr": 0.02575755989310675, "acc_norm": 0.22641509433962265, "acc_norm_stderr": 0.02575755989310675 }, "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": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "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": 0.20809248554913296, "acc_stderr": 0.030952890217749874, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749874 }, "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": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "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": 0.23684210526315788, "acc_stderr": 0.039994238792813365, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813365 }, "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": 0.20899470899470898, "acc_stderr": 0.02094048156533486, "acc_norm": 0.20899470899470898, "acc_norm_stderr": 0.02094048156533486 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.29365079365079366, "acc_stderr": 0.04073524322147126, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.04073524322147126 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.18, "acc_stderr": 0.038612291966536934, "acc_norm": 0.18, "acc_norm_stderr": 0.038612291966536934 }, "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": 0.15270935960591134, "acc_stderr": 0.02530890453938063, "acc_norm": 0.15270935960591134, "acc_norm_stderr": 0.02530890453938063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.18181818181818182, "acc_stderr": 0.027479603010538797, "acc_norm": 0.18181818181818182, "acc_norm_stderr": 0.027479603010538797 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860664, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860664 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.19743589743589743, "acc_stderr": 0.02018264696867484, "acc_norm": 0.19743589743589743, "acc_norm_stderr": 0.02018264696867484 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2111111111111111, "acc_stderr": 0.024882116857
