open-llm-leaderboard-old/details_Kquant03__Hippolyta-7B-bf16
收藏数据集概述
数据集来源
该数据集是在评估模型 Kquant03/Hippolyta-7B-bf16 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。
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 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_Kquant03__Hippolyta-7B-bf16", "harness_winogrande_5", split="train")
最新结果
最新结果概览
以下是 2024-01-13T16:20:49.648715 运行的最新结果：
python { "all": { "acc": 0.5710190127480856, "acc_stderr": 0.03332687168090072, "acc_norm": 0.5813613001110371, "acc_norm_stderr": 0.03416710231417157, "mc1": 0.390452876376989, "mc1_stderr": 0.017078230743431438, "mc2": 0.5573938277943279, "mc2_stderr": 0.015496591664705626 }, "harness|arc:challenge|25": { "acc": 0.5691126279863481, "acc_stderr": 0.014471133392642478, "acc_norm": 0.60580204778157, "acc_norm_stderr": 0.014280522667467325 }, "harness|hellaswag|10": { "acc": 0.6106353316072496, "acc_stderr": 0.004866096880941442, "acc_norm": 0.7998406691894046, "acc_norm_stderr": 0.003993017173367213 }, "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": 0.5925925925925926, "acc_stderr": 0.04244633238353228, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353228 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6052631578947368, "acc_stderr": 0.039777499346220734, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.039777499346220734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6566037735849056, "acc_stderr": 0.02922452646912479, "acc_norm": 0.6566037735849056, "acc_norm_stderr": 0.02922452646912479 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.038990736873573344, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.038990736873573344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.45, "acc_stderr": 0.04999999999999999, "acc_norm": 0.45, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5491329479768786, "acc_stderr": 0.0379401267469703, "acc_norm": 0.5491329479768786, "acc_norm_stderr": 0.0379401267469703 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.29411764705882354, "acc_stderr": 0.04533838195929777, "acc_norm": 0.29411764705882354, "acc_norm_stderr": 0.04533838195929777 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.0446196043338474, "acc_norm": 0.73, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4808510638297872, "acc_stderr": 0.03266204299064678, "acc_norm": 0.4808510638297872, "acc_norm_stderr": 0.03266204299064678 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.04615186962583703, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.04615186962583703 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37037037037037035, "acc_stderr": 0.02487081525105709, "acc_norm": 0.37037037037037035, "acc_norm_stderr": 0.02487081525105709 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3492063492063492, "acc_stderr": 0.04263906892795133, "acc_norm": 0.3492063492063492, "acc_norm_stderr": 0.04263906892795133 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6483870967741936, "acc_stderr": 0.027162537826948458, "acc_norm": 0.6483870967741936, "acc_norm_stderr": 0.027162537826948458 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4088669950738916, "acc_stderr": 0.034590588158832314, "acc_norm": 0.4088669950738916, "acc_norm_stderr": 0.034590588158832314 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.58, "acc_stderr": 0.04960449637488584, "acc_norm": 0.58, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7151515151515152, "acc_stderr": 0.03524390844511781, "acc_norm": 0.7151515151515152, "acc_norm_stderr": 0.03524390844511781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.029857515673386417, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.029857515673386417 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8341968911917098, "acc_stderr": 0.026839845022314415, "acc_norm": 0.8341968911917098, "acc_norm_stderr": 0.026839845022314415 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5897435897435898, "acc_stderr": 0.0249393139069408, "acc_norm": 0.5897435897435898, "acc_norm_stderr": 0.0249393139069408 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.027940457136228405, "acc_norm": 0.3, "acc_norm_stderr": 0.0279404571362284
