open-llm-leaderboard-old/details_DreadPoor__complect-7B-slerp

该数据集是在模型DreadPoor/complect-7B-slerp的评估运行期间自动创建的，用于在Open LLM Leaderboard上进行评估。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为一个特定的分割存储在配置中，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，数据集还包含一个名为results的配置，用于存储所有运行的聚合结果，并在Open LLM Leaderboard上显示聚合指标。

原始信息汇总

数据集概述

数据集简介

该数据集是在模型DreadPoor/complect-7B-slerp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。
• 创建来源：数据集来自1次运行，每个运行在每个配置中作为一个特定的分割，分割名称使用运行的时间戳。
• 训练分割："train"分割始终指向最新的结果。
• 结果配置：一个额外的配置"results"存储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_DreadPoor__complect-7B-slerp", "harness_winogrande_5", split="train")

最新结果

以下是2024-03-07T15:30:34.734820运行的最新结果：

python { "all": { "acc": 0.654501445035387, "acc_stderr": 0.032055837406835125, "acc_norm": 0.654143289555927, "acc_norm_stderr": 0.032724844511645854, "mc1": 0.5605875152998776, "mc1_stderr": 0.017374520482513704, "mc2": 0.711356205167106, "mc2_stderr": 0.01471283539228549 }, "harness|arc:challenge|25": { "acc": 0.6953924914675768, "acc_stderr": 0.013449522109932487, "acc_norm": 0.7226962457337884, "acc_norm_stderr": 0.013082095839059376 }, "harness|hellaswag|10": { "acc": 0.7094204341764588, "acc_stderr": 0.004531019159414106, "acc_norm": 0.8818960366460864, "acc_norm_stderr": 0.003220716126685026 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6370370370370371, "acc_stderr": 0.041539484047423976, "acc_norm": 0.6370370370370371, "acc_norm_stderr": 0.041539484047423976 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6981132075471698, "acc_stderr": 0.028254200344438662, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.028254200344438662 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6820809248554913, "acc_stderr": 0.0355068398916558, "acc_norm": 0.6820809248554913, "acc_norm_stderr": 0.0355068398916558 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4411764705882353, "acc_stderr": 0.049406356306056595, "acc_norm": 0.4411764705882353, "acc_norm_stderr": 0.049406356306056595 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5787234042553191, "acc_stderr": 0.03227834510146268, "acc_norm": 0.5787234042553191, "acc_norm_stderr": 0.03227834510146268 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5087719298245614, "acc_stderr": 0.04702880432049615, "acc_norm": 0.5087719298245614, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370332, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370332 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41798941798941797, "acc_stderr": 0.025402555503260912, "acc_norm": 0.41798941798941797, "acc_norm_stderr": 0.025402555503260912 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "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": 0.7806451612903226, "acc_stderr": 0.023540799358723295, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723295 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.03514528562175008, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.03192271569548301, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.803030303030303, "acc_stderr": 0.028335609732463362, "acc_norm": 0.803030303030303, "acc_norm_stderr": 0.028335609732463362 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033484, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033484 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6717948717948717, "acc_stderr": 0.023807633198657266, "acc_norm": 0.6717948717948717, "acc_norm_stderr": 0.023807633198657266 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.02882088466625326, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.02882088466625326 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6764705882352942, "acc_stderr": 0.030388353551886783, "acc_norm": 0.6764705882352942, "acc_norm_stderr": 0.030388353551886783 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3841059602649007, "acc_stderr": 0.03971301814719197, "acc_norm": 0.3841059602649007, "acc_norm_stderr": 0.03971301814719197 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8403669724770643, "acc_stderr": 0.015703498348461766, "acc_norm": 0.8403669724770643, "acc_norm_stderr": 0.015703498348461766 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5, "acc_stderr": 0.034099716973523674, "acc_norm": 0.5, "acc_norm_stderr": 0.034099716973523674 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.8382352941176471, "acc_stderr": 0.025845017986926917, "acc_norm": 0.8382352941176471, "acc_norm_stderr": 0.025845017986926917 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.8185654008438819, "acc_stderr": 0.02508596114457966, "acc_norm": 0.8185654008438819, "acc_norm_stderr": 0.02508596114457966 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6860986547085202, "acc_stderr": 0.031146796482972465, "acc_norm": 0.6860986547085202, "acc_norm_stderr": 0.031146796482972465 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.8015267175572519, "acc_stderr": 0.034981493854624714, "acc_norm": 0.8015267175572519, "acc_norm_stderr": 0.034981493854624714 }, "harness|hendrycksTest-international_law|5": { "acc": 0.7851239669421488, "acc_stderr": 0.037494924487096966, "acc_norm": 0.7851239669421488, "acc_norm_stderr": 0.037494924487096966 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7592592592592593, "acc_stderr": 0.04133119440243839, "acc_norm": 0.7592592592592593, "acc_norm_stderr": 0.04133119440243839 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7730061349693251, "acc_stderr": 0.03291099578615769, "acc_norm": 0.7730061349693251, "acc_norm_stderr": 0.03291099578615769 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.42857142857142855, "acc_stderr": 0.04697113923010212, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.04697113923010212 }, "harness|hendrycksTest-management|5": { "acc": 0.7766990291262136, "acc_stderr": 0.04123553189891431, "acc_norm": 0.7766990291262136, "acc_norm_stderr": 0.04123553189891431 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8760683760683761, "acc_stderr": 0.021586494001281365, "acc_norm": 0.8760683760683761, "acc_norm_stderr": 0.021586494001281365 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8263090676883781, "acc_stderr": 0.013547415658662264, "acc_norm": 0.8263090676883781, "acc_norm_stderr": 0.013547415658662264 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7456647398843931, "acc_stderr": 0.023445826276545543, "acc_norm": 0.7456647398843931, "acc_norm_stderr": 0.023445826276545543 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.40893854748603353, "acc_stderr": 0.01644283065471554, "acc_norm": 0.40893854748603353, "acc_norm_stderr": 0.01644283065471554 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7091503267973857, "acc_stderr": 0.02600480036395213, "acc_norm": 0.7091503267973857, "acc_norm_stderr": 0.02600480036395213 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7138263665594855, "acc_stderr": 0.025670259242188933, "acc_norm": 0.7138263665594855, "acc_norm_stderr": 0.025670259242188933 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7438271604938271, "acc_stderr": 0.0242885336377261, "acc_norm": 0.7438271604938271, "acc_norm_stderr": 0.0242885336377261 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.5070921985815603, "acc_stderr": 0.02982449855912901, "acc_norm": 0.5070921985815603, "acc_norm_stderr": 0.02982449855912901 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4726205997392438, "acc_stderr": 0.012751075788015055, "acc_norm": 0.4726205997392438, "acc_norm_stderr": 0.012751075788015055 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6838235294117647, "acc_stderr": 0.028245687391462927, "acc_norm": 0.6838235294117647, "acc_norm_stderr": 0.028245687391462927 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.6781045751633987, "acc_stderr": 0.018901015322093092, "acc_norm": 0.6781045751633987, "acc_norm_stderr": 0.018901015322093092 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6818181818181818, "acc_stderr": 0.04461272175910509, "acc_norm": 0.6818181818181818, "acc_norm_stderr": 0.04461272175910509 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7346938775510204, "acc_stderr": 0.0282638899437846, "acc_norm": 0.7346938775510204, "acc_norm_stderr": 0.0282638899437846 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8258706467661692, "acc_stderr": 0.026814951200421603, "acc_norm": 0.8258706467661692, "acc_norm_stderr": 0.026814951200421603 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.86, "acc_stderr": 0.0348735088019777, "acc_norm": 0.86, "acc_norm_stderr": 0.0348735088019777 }, "harness|hendrycksTest-virology|5": { "acc": 0.5542168674698795, "acc_stderr": 0.03869543323472101, "acc_norm": 0.5542168674698795, "acc_norm_stderr": 0.03869543323472101 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8421052631578947, "acc_stderr": 0.027966785859160893, "acc_norm": 0.8421052631578947, "acc_norm_stderr": 0.027966785859160893 }, "harness|truthfulqa:mc|0": { "mc1": 0.5605875152998776, "mc1_stderr": 0.017374520482513704, "mc2": 0.711356205167106, "mc2_stderr": 0.01471283539228549 }, "harness|winogrande|5": { "acc": 0.8453038674033149, "acc_stderr": 0.010163172650433535 }, "harness|gsm8k|5": { "acc": 0.6846095526914329, "acc_stderr": 0.012799353675801834 } }