open-llm-leaderboard-old/details_Felladrin__TinyMistral-248M-Chat-v2
收藏数据集概述
数据集简介
该数据集是在模型 Felladrin/TinyMistral-248M-Chat-v2 的评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。
- 数据集从 1 次运行中创建，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。
- 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 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_Felladrin__TinyMistral-248M-Chat-v2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-02T21:32:49.022074 运行的最新结果：
python { "all": { "acc": 0.23548173558413027, "acc_stderr": 0.029992044204323092, "acc_norm": 0.2358268812315828, "acc_norm_stderr": 0.030783740280310598, "mc1": 0.22031823745410037, "mc1_stderr": 0.014509045171487295, "mc2": 0.41322892036563413, "mc2_stderr": 0.015009018402062363 }, "harness|arc:challenge|25": { "acc": 0.19539249146757678, "acc_stderr": 0.011586907189952911, "acc_norm": 0.23293515358361774, "acc_norm_stderr": 0.01235250704261741 }, "harness|hellaswag|10": { "acc": 0.2719577773351922, "acc_stderr": 0.004440588618232711, "acc_norm": 0.27394941246763593, "acc_norm_stderr": 0.004450718673552664 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.32592592592592595, "acc_stderr": 0.040491220417025055, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.19736842105263158, "acc_stderr": 0.03238981601699397, "acc_norm": 0.19736842105263158, "acc_norm_stderr": 0.03238981601699397 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.21132075471698114, "acc_stderr": 0.025125766484827842, "acc_norm": 0.21132075471698114, "acc_norm_stderr": 0.025125766484827842 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.20833333333333334, "acc_stderr": 0.033961162058453336, "acc_norm": 0.20833333333333334, "acc_norm_stderr": 0.033961162058453336 }, "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": 0.17, "acc_stderr": 0.0377525168068637, "acc_norm": 0.17, "acc_norm_stderr": 0.0377525168068637 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.19, "acc_stderr": 0.03942772444036623, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036623 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.0309528902177499, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.0309528902177499 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.04280105837364396, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.04280105837364396 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28936170212765955, "acc_stderr": 0.029644006577009618, "acc_norm": 0.28936170212765955, "acc_norm_stderr": 0.029644006577009618 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.04227054451232199, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.04227054451232199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2830687830687831, "acc_stderr": 0.023201392938194978, "acc_norm": 0.2830687830687831, "acc_norm_stderr": 0.023201392938194978 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.23015873015873015, "acc_stderr": 0.03764950879790605, "acc_norm": 0.23015873015873015, "acc_norm_stderr": 0.03764950879790605 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.15, "acc_stderr": 0.0358870281282637, "acc_norm": 0.15, "acc_norm_stderr": 0.0358870281282637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2645161290322581, "acc_stderr": 0.025091892378859275, "acc_norm": 0.2645161290322581, "acc_norm_stderr": 0.025091892378859275 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.27586206896551724, "acc_stderr": 0.03144712581678242, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.03144712581678242 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.26, "acc_stderr": 0.04408440022768077, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768077 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.2787878787878788, "acc_stderr": 0.035014387062967806, "acc_norm": 0.2787878787878788, "acc_norm_stderr": 0.035014387062967806 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2878787878787879, "acc_stderr": 0.03225883512300992, "acc_norm": 0.2878787878787879, "acc_norm_stderr": 0.03225883512300992 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.22797927461139897, "acc_stderr": 0.030276909945178253, "acc_norm": 0.22797927461139897, "acc_norm_stderr": 0.030276909945178253 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.21794871794871795, "acc_stderr": 0.02093244577446318, "acc_norm": 0.21794871794871795, "acc_norm_stderr": 0.02093244577446318 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23333333333333334, "acc_stderr": 0.02578787
