open-llm-leaderboard-old/details_Dans-DiscountModels__TinyMistral-v2.5-MiniPile-Guidelines-E1
收藏数据集概述
数据集简介
该数据集是在评估模型 Dans-DiscountModels/TinyMistral-v2.5-MiniPile-Guidelines-E1 在 Open LLM Leaderboard 上的自动创建的。
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。每个运行可以在每个配置中作为一个特定的分割找到，分割名称使用运行的时间戳。
- "train" 分割总是指向最新的结果。
- 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_Dans-DiscountModels__TinyMistral-v2.5-MiniPile-Guidelines-E1", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-02-01T21:44:48.551629 的摘要：
python { "all": { "acc": 0.235616909983485, "acc_stderr": 0.030096196864815804, "acc_norm": 0.23617812988980863, "acc_norm_stderr": 0.030895352600212644, "mc1": 0.2460220318237454, "mc1_stderr": 0.015077219200662578, "mc2": 0.49848823283731625, "mc2_stderr": 0.016449164481650215 }, "harness|arc:challenge|25": { "acc": 0.2090443686006826, "acc_stderr": 0.011882746987406458, "acc_norm": 0.2645051194539249, "acc_norm_stderr": 0.012889272949313366 }, "harness|hellaswag|10": { "acc": 0.25632344154550885, "acc_stderr": 0.004357101984278612, "acc_norm": 0.2568213503286198, "acc_norm_stderr": 0.00435987151963954 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.18518518518518517, "acc_stderr": 0.03355677216313141, "acc_norm": 0.18518518518518517, "acc_norm_stderr": 0.03355677216313141 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.24150943396226415, "acc_stderr": 0.026341480371118376, "acc_norm": 0.24150943396226415, "acc_norm_stderr": 0.026341480371118376 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.25, "acc_stderr": 0.03621034121889507, "acc_norm": 0.25, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.23, "acc_stderr": 0.04229525846816507, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2023121387283237, "acc_stderr": 0.03063114553919882, "acc_norm": 0.2023121387283237, "acc_norm_stderr": 0.03063114553919882 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.26382978723404255, "acc_stderr": 0.028809989854102973, "acc_norm": 0.26382978723404255, "acc_norm_stderr": 0.028809989854102973 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21052631578947367, "acc_stderr": 0.038351539543994194, "acc_norm": 0.21052631578947367, "acc_norm_stderr": 0.038351539543994194 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2413793103448276, "acc_stderr": 0.03565998174135302, "acc_norm": 0.2413793103448276, "acc_norm_stderr": 0.03565998174135302 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.20899470899470898, "acc_stderr": 0.02094048156533486, "acc_norm": 0.20899470899470898, "acc_norm_stderr": 0.02094048156533486 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2857142857142857, "acc_stderr": 0.04040610178208841, "acc_norm": 0.2857142857142857, "acc_norm_stderr": 0.04040610178208841 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.19, "acc_stderr": 0.03942772444036625, "acc_norm": 0.19, "acc_norm_stderr": 0.03942772444036625 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.1774193548387097, "acc_stderr": 0.02173254068932927, "acc_norm": 0.1774193548387097, "acc_norm_stderr": 0.02173254068932927 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.18719211822660098, "acc_stderr": 0.027444924966882618, "acc_norm": 0.18719211822660098, "acc_norm_stderr": 0.027444924966882618 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2222222222222222, "acc_stderr": 0.029620227874790482, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.029620227874790482 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.19689119170984457, "acc_stderr": 0.028697873971860664, "acc_norm": 0.19689119170984457, "acc_norm_stderr": 0.028697873971860664 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2, "acc_stderr": 0.020280805062535722, "acc_norm": 0.2, "acc_norm_stderr": 0.020280805062535722 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2111111111111111, "acc_stderr": 0.024882116857655075, "acc_norm": 0.2111111111111
