open-llm-leaderboard-old/details_luffycodes__vicuna-class-shishya-ac-hal-13b-ep3
收藏数据集概述
数据集简介
该数据集是在评估模型 luffycodes/vicuna-class-shishya-ac-hal-13b-ep3 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
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：数据集由1次运行创建，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_luffycodes__vicuna-class-shishya-ac-hal-13b-ep3", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果 的摘要：
python { "all": { "acc": 0.5542525215859695, "acc_stderr": 0.03349073743939158, "acc_norm": 0.5645913429036128, "acc_norm_stderr": 0.034401518822204755, "mc1": 0.2692778457772338, "mc1_stderr": 0.015528566637087283, "mc2": 0.3932031444895361, "mc2_stderr": 0.01464338174530395 }, "harness|arc:challenge|25": { "acc": 0.44283276450511944, "acc_stderr": 0.014515573873348897, "acc_norm": 0.48464163822525597, "acc_norm_stderr": 0.014604496129394908 }, "harness|hellaswag|10": { "acc": 0.6133240390360486, "acc_stderr": 0.004859930926500306, "acc_norm": 0.8078072097191794, "acc_norm_stderr": 0.003932184843841661 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.04688261722621502, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621502 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4740740740740741, "acc_stderr": 0.04313531696750574, "acc_norm": 0.4740740740740741, "acc_norm_stderr": 0.04313531696750574 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5592105263157895, "acc_stderr": 0.04040311062490436, "acc_norm": 0.5592105263157895, "acc_norm_stderr": 0.04040311062490436 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6150943396226415, "acc_stderr": 0.02994649856769995, "acc_norm": 0.6150943396226415, "acc_norm_stderr": 0.02994649856769995 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5763888888888888, "acc_stderr": 0.041321250197233685, "acc_norm": 0.5763888888888888, "acc_norm_stderr": 0.041321250197233685 }, "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": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "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": 0.5491329479768786, "acc_stderr": 0.0379401267469703, "acc_norm": 0.5491329479768786, "acc_norm_stderr": 0.0379401267469703 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.04755129616062946, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.04755129616062946 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4425531914893617, "acc_stderr": 0.03246956919789958, "acc_norm": 0.4425531914893617, "acc_norm_stderr": 0.03246956919789958 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.041424397194893624, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.041424397194893624 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.041665675771015785, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.041665675771015785 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3306878306878307, "acc_stderr": 0.024229965298425082, "acc_norm": 0.3306878306878307, "acc_norm_stderr": 0.024229965298425082 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3412698412698413, "acc_stderr": 0.04240799327574924, "acc_norm": 0.3412698412698413, "acc_norm_stderr": 0.04240799327574924 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6387096774193548, "acc_stderr": 0.027327548447957536, "acc_norm": 0.6387096774193548, "acc_norm_stderr": 0.027327548447957536 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876105, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6787878787878788, "acc_stderr": 0.036462049632538115, "acc_norm": 0.6787878787878788, "acc_norm_stderr": 0.036462049632538115 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6767676767676768, "acc_stderr": 0.03332299921070643, "acc_norm": 0.6767676767676768, "acc_norm_stderr": 0.03332299921070643 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7927461139896373, "acc_stderr": 0.02925282329180363, "acc_norm": 0.7927461139896373, "acc_norm_stderr": 0.02925282329180363 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5717948717948718, "acc_stderr": 0.025088301454694834, "acc_norm": 0.5717948717948718, "acc_norm_stderr": 0.025088301454694834 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3037037037037037, "acc_stderr": 0.028037929969114982, "acc_norm": 0.3037037037037037, "acc_norm_stderr": 0.02803
