open-llm-leaderboard-old/details_abdulrahman-nuzha__finetuned-llama-v2.0
收藏数据集概述
数据集摘要
该数据集是在评估模型 abdulrahman-nuzha/finetuned-llama-v2.0 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 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拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_abdulrahman-nuzha__finetuned-llama-v2.0", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-10T10:47:40.022995 运行的最新结果： python { "all": { "acc": 0.43945994951550066, "acc_stderr": 0.034385529407471936, "acc_norm": 0.4442918982351828, "acc_norm_stderr": 0.035190222707291795, "mc1": 0.24969400244798043, "mc1_stderr": 0.015152286907148128, "mc2": 0.3908033560283727, "mc2_stderr": 0.013656125379191442 }, "harness|arc:challenge|25": { "acc": 0.4803754266211604, "acc_stderr": 0.014600132075947087, "acc_norm": 0.5315699658703071, "acc_norm_stderr": 0.014582236460866978 }, "harness|hellaswag|10": { "acc": 0.5789683330013942, "acc_stderr": 0.0049271558825981845, "acc_norm": 0.7775343557060347, "acc_norm_stderr": 0.0041505226302310265 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.42962962962962964, "acc_stderr": 0.04276349494376599, "acc_norm": 0.42962962962962964, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.40789473684210525, "acc_stderr": 0.03999309712777471, "acc_norm": 0.40789473684210525, "acc_norm_stderr": 0.03999309712777471 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.44528301886792454, "acc_stderr": 0.030588052974270655, "acc_norm": 0.44528301886792454, "acc_norm_stderr": 0.030588052974270655 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04155319955593146, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04155319955593146 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.37572254335260113, "acc_stderr": 0.036928207672648664, "acc_norm": 0.37572254335260113, "acc_norm_stderr": 0.036928207672648664 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.18627450980392157, "acc_stderr": 0.038739587141493524, "acc_norm": 0.18627450980392157, "acc_norm_stderr": 0.038739587141493524 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.58, "acc_stderr": 0.04960449637488583, "acc_norm": 0.58, "acc_norm_stderr": 0.04960449637488583 }, "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": 0.2982456140350877, "acc_stderr": 0.04303684033537315, "acc_norm": 0.2982456140350877, "acc_norm_stderr": 0.04303684033537315 }, "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": 0.24074074074074073, "acc_stderr": 0.02201908001221789, "acc_norm": 0.24074074074074073, "acc_norm_stderr": 0.02201908001221789 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04216370213557835, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04216370213557835 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4290322580645161, "acc_stderr": 0.02815603653823321, "acc_norm": 0.4290322580645161, "acc_norm_stderr": 0.02815603653823321 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3448275862068966, "acc_stderr": 0.03344283744280458, "acc_norm": 0.3448275862068966, "acc_norm_stderr": 0.03344283744280458 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.5636363636363636, "acc_stderr": 0.03872592983524754, "acc_norm": 0.5636363636363636, "acc_norm_stderr": 0.03872592983524754 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.4696969696969697, "acc_stderr": 0.03555804051763929, "acc_norm": 0.4696969696969697, "acc_norm_stderr": 0.03555804051763929 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.6321243523316062, "acc_stderr": 0.034801756684660366, "acc_norm": 0.6321243523316062, "acc_norm_stderr": 0.034801756684660366 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4, "acc_stderr": 0.024838811988033158, "acc_norm": 0.4, "acc_norm_stderr": 0.024838811988033158 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24814814814814815, "acc_stderr": 0.0263357394040558, "acc_norm": 0.248148148148
