open-llm-leaderboard-old/details_ewqr2130__alignment-handbook-zephyr-7b_ppo_5e7step_102
收藏数据集概述
数据集摘要
该数据集是在模型 ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_102 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 63 个配置组成，每个配置对应一个评估任务。
数据集结构
数据集包含 63 个配置，每个配置对应一个评估任务。每个配置包含多个分割，分割名称使用运行的时间戳。"train" 分割始终指向最新的结果。此外，还有一个名为 "results" 的配置，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
以下是加载数据集的示例代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_ewqr2130__alignment-handbook-zephyr-7b_ppo_5e7step_102", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-19T20:51:30.174111 运行的最新结果： python { "all": { "acc": 0.5942231513843124, "acc_stderr": 0.03336228056397976, "acc_norm": 0.6000481834929137, "acc_norm_stderr": 0.03405843191633746, "mc1": 0.28151774785801714, "mc1_stderr": 0.01574402724825605, "mc2": 0.41558392287111307, "mc2_stderr": 0.01541776331607284 }, "harness|arc:challenge|25": { "acc": 0.5639931740614335, "acc_stderr": 0.014491225699230916, "acc_norm": 0.5921501706484642, "acc_norm_stderr": 0.014361097288449703 }, "harness|hellaswag|10": { "acc": 0.6238797052380004, "acc_stderr": 0.00483420796406132, "acc_norm": 0.8245369448317068, "acc_norm_stderr": 0.0037958533012439908 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.042763494943765995, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.042763494943765995 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.029067220146644826, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.029067220146644826 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6666666666666666, "acc_stderr": 0.03942082639927213, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.03942082639927213 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082636, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5106382978723404, "acc_stderr": 0.03267862331014063, "acc_norm": 0.5106382978723404, "acc_norm_stderr": 0.03267862331014063 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.046151869625837026, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.046151869625837026 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5586206896551724, "acc_stderr": 0.04137931034482757, "acc_norm": 0.5586206896551724, "acc_norm_stderr": 0.04137931034482757 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.38095238095238093, "acc_stderr": 0.02501074911613759, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.02501074911613759 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.373015873015873, "acc_stderr": 0.04325506042017086, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.04325506042017086 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7225806451612903, "acc_stderr": 0.025470196835900055, "acc_norm": 0.7225806451612903, "acc_norm_stderr": 0.025470196835900055 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.03517603540361008, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.03517603540361008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7323232323232324, "acc_stderr": 0.03154449888270285, "acc_norm": 0.7323232323232324, "acc_norm_stderr": 0.03154449888270285 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.029778663037752954, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.029778663037752954 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5820512820512821, "acc_stderr": 0.02500732988246121, "acc_norm": 0.5820512820512821, "acc_norm_stderr": 0.02500732988246121 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34074074074074073, "acc_stderr": 0.0288977
