open-llm-leaderboard-old/details_M4-ai__tau-0.5B
收藏数据集概述
数据集简介
该数据集是在对模型 M4-ai/tau-0.5B 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
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。
- 运行次数：数据集从2次运行中创建，每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 训练分割："train" 分割始终指向最新的结果。
- 结果配置：一个额外的 "results" 配置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_M4-ai__tau-0.5B", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-09T19:01:53.825148 运行 的最新结果：
python { "all": { "acc": 0.371271329092256, "acc_stderr": 0.03409232367144655, "acc_norm": 0.3747093594878918, "acc_norm_stderr": 0.03488231014505325, "mc1": 0.24357405140758873, "mc1_stderr": 0.015026354824910782, "mc2": 0.39391928012221666, "mc2_stderr": 0.014285869122274612 }, "harness|arc:challenge|25": { "acc": 0.2645051194539249, "acc_stderr": 0.012889272949313368, "acc_norm": 0.2901023890784983, "acc_norm_stderr": 0.013261573677520773 }, "harness|hellaswag|10": { "acc": 0.3737303326030671, "acc_stderr": 0.0048280457747349, "acc_norm": 0.47450707030472017, "acc_norm_stderr": 0.004983291578289043 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.28888888888888886, "acc_stderr": 0.0391545063041425, "acc_norm": 0.28888888888888886, "acc_norm_stderr": 0.0391545063041425 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3684210526315789, "acc_stderr": 0.03925523381052932, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.03925523381052932 }, "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": 0.43018867924528303, "acc_stderr": 0.030471445867183235, "acc_norm": 0.43018867924528303, "acc_norm_stderr": 0.030471445867183235 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3194444444444444, "acc_stderr": 0.038990736873573344, "acc_norm": 0.3194444444444444, "acc_norm_stderr": 0.038990736873573344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.27, "acc_stderr": 0.0446196043338474, "acc_norm": 0.27, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3815028901734104, "acc_stderr": 0.03703851193099521, "acc_norm": 0.3815028901734104, "acc_norm_stderr": 0.03703851193099521 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.043898699568087785, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.043898699568087785 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.33617021276595743, "acc_stderr": 0.030881618520676942, "acc_norm": 0.33617021276595743, "acc_norm_stderr": 0.030881618520676942 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2807017543859649, "acc_stderr": 0.042270544512322004, "acc_norm": 0.2807017543859649, "acc_norm_stderr": 0.042270544512322004 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4, "acc_stderr": 0.04082482904638628, "acc_norm": 0.4, "acc_norm_stderr": 0.04082482904638628 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.30158730158730157, "acc_stderr": 0.023636975996101806, "acc_norm": 0.30158730158730157, "acc_norm_stderr": 0.023636975996101806 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2777777777777778, "acc_stderr": 0.040061680838488774, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.040061680838488774 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4258064516129032, "acc_stderr": 0.0281291127091659, "acc_norm": 0.4258064516129032, "acc_norm_stderr": 0.0281291127091659 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.28078817733990147, "acc_stderr": 0.031618563353586086, "acc_norm": 0.28078817733990147, "acc_norm_stderr": 0.031618563353586086 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4727272727272727, "acc_stderr": 0.03898531605579419, "acc_norm": 0.4727272727272727, "acc_norm_stderr": 0.03898531605579419 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5252525252525253, "acc_stderr": 0.03557806245087314, "acc_norm": 0.5252525252525253, "acc_norm_stderr": 0.03557806245087314 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.46632124352331605, "acc_stderr": 0.03600244069867178, "acc_norm": 0.46632124352331605, "acc_norm_stderr": 0.03600244069867178 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4076923076923077, "acc_stderr": 0.02491524398598785, "acc_norm": 0.4076923076923077, "acc_norm_stderr": 0.02491524398598785 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34444444444444444, "acc_stderr": 0.028972648884844267, "acc_norm": 0.34444444444444444, "acc_norm_stderr": 0.02897264
