open-llm-leaderboard-old/details_rishiraj__smol-3b
收藏数据集概述
数据集来源
该数据集是在对模型 rishiraj/smol-3b 进行评估运行期间自动创建的，评估运行在 Open LLM Leaderboard 上进行。
数据集组成
数据集由 63 个配置组成，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" 分割总是指向最新的结果。
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_rishiraj__smol-3b", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-13T10:26:39.414520 运行的最新结果：
python { "all": { "acc": 0.4630403817848583, "acc_stderr": 0.03471311735087895, "acc_norm": 0.467024043140488, "acc_norm_stderr": 0.035458188509216476, "mc1": 0.32313341493268055, "mc1_stderr": 0.0163718362864546, "mc2": 0.5073211090135596, "mc2_stderr": 0.015470937650792245 }, "harness|arc:challenge|25": { "acc": 0.42662116040955633, "acc_stderr": 0.014453185592920293, "acc_norm": 0.46331058020477817, "acc_norm_stderr": 0.014572000527756998 }, "harness|hellaswag|10": { "acc": 0.510157339175463, "acc_stderr": 0.004988751698341138, "acc_norm": 0.6823341963752241, "acc_norm_stderr": 0.004646172373100999 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04292596718256981, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04292596718256981 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04063302731486671, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04063302731486671 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5245283018867924, "acc_stderr": 0.030735822206205608, "acc_norm": 0.5245283018867924, "acc_norm_stderr": 0.030735822206205608 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5347222222222222, "acc_stderr": 0.04171115858181618, "acc_norm": 0.5347222222222222, "acc_norm_stderr": 0.04171115858181618 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4161849710982659, "acc_stderr": 0.03758517775404948, "acc_norm": 0.4161849710982659, "acc_norm_stderr": 0.03758517775404948 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.28431372549019607, "acc_stderr": 0.04488482852329017, "acc_norm": 0.28431372549019607, "acc_norm_stderr": 0.04488482852329017 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.3446808510638298, "acc_stderr": 0.031068985963122145, "acc_norm": 0.3446808510638298, "acc_norm_stderr": 0.031068985963122145 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.30701754385964913, "acc_stderr": 0.04339138322579861, "acc_norm": 0.30701754385964913, "acc_norm_stderr": 0.04339138322579861 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.46206896551724136, "acc_stderr": 0.041546596717075474, "acc_norm": 0.46206896551724136, "acc_norm_stderr": 0.041546596717075474 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2804232804232804, "acc_stderr": 0.023135287974325625, "acc_norm": 0.2804232804232804, "acc_norm_stderr": 0.023135287974325625 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3253968253968254, "acc_stderr": 0.04190596438871136, "acc_norm": 0.3253968253968254, "acc_norm_stderr": 0.04190596438871136 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.24, "acc_stderr": 0.04292346959909283, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.532258064516129, "acc_stderr": 0.02838474778881333, "acc_norm": 0.532258064516129, "acc_norm_stderr": 0.02838474778881333 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.37438423645320196, "acc_stderr": 0.03405155380561952, "acc_norm": 0.37438423645320196, "acc_norm_stderr": 0.03405155380561952 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6060606060606061, "acc_stderr": 0.03815494308688931, "acc_norm": 0.6060606060606061, "acc_norm_stderr": 0.03815494308688931 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5303030303030303, "acc_stderr": 0.03555804051763929, "acc_norm": 0.5303030303030303, "acc_norm_stderr": 0.03555804051763929 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6373056994818653, "acc_stderr": 0.03469713791704371, "acc_norm": 0.6373056994818653, "acc_norm_stderr": 0.03469713791704371 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4282051282051282, "acc_stderr": 0.025088301454694827, "acc_norm": 0.4282051282051282, "acc_norm_stderr": 0.025088301454694827 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2222222222222222, "acc_stderr": 0.025348097468097845, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.0
