open-llm-leaderboard-old/details_Josephgflowers__Tinyllama-1.5B-Cinder-Test-2
收藏数据集概述
数据集摘要
该数据集是在对模型 Josephgflowers/Tinyllama-1.5B-Cinder-Test-2 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
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 2 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。
- 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_Josephgflowers__Tinyllama-1.5B-Cinder-Test-2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-05T21:22:09.465979 运行的最新结果：
python { "all": { "acc": 0.2705480629693628, "acc_stderr": 0.031211817677101388, "acc_norm": 0.2722219261351411, "acc_norm_stderr": 0.03204316052559818, "mc1": 0.24112607099143207, "mc1_stderr": 0.01497482727975233, "mc2": 0.4055707932475926, "mc2_stderr": 0.014734925050237744 }, "harness|arc:challenge|25": { "acc": 0.32337883959044367, "acc_stderr": 0.01366942163001213, "acc_norm": 0.35494880546075086, "acc_norm_stderr": 0.013983036904094092 }, "harness|hellaswag|10": { "acc": 0.39693288189603665, "acc_stderr": 0.004882619484166598, "acc_norm": 0.5189205337582155, "acc_norm_stderr": 0.004986207581862946 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816507, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.25, "acc_stderr": 0.03523807393012047, "acc_norm": 0.25, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.28679245283018867, "acc_stderr": 0.02783491252754408, "acc_norm": 0.28679245283018867, "acc_norm_stderr": 0.02783491252754408 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.24305555555555555, "acc_stderr": 0.03586879280080342, "acc_norm": 0.24305555555555555, "acc_norm_stderr": 0.03586879280080342 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.21965317919075145, "acc_stderr": 0.031568093627031744, "acc_norm": 0.21965317919075145, "acc_norm_stderr": 0.031568093627031744 }, "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": 0.21, "acc_stderr": 0.04093601807403326, "acc_norm": 0.21, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2680851063829787, "acc_stderr": 0.02895734278834235, "acc_norm": 0.2680851063829787, "acc_norm_stderr": 0.02895734278834235 }, "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": 0.23448275862068965, "acc_stderr": 0.035306258743465914, "acc_norm": 0.23448275862068965, "acc_norm_stderr": 0.035306258743465914 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "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": 0.15, "acc_stderr": 0.03588702812826371, "acc_norm": 0.15, "acc_norm_stderr": 0.03588702812826371 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3161290322580645, "acc_stderr": 0.02645087448904277, "acc_norm": 0.3161290322580645, "acc_norm_stderr": 0.02645087448904277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.30049261083743845, "acc_stderr": 0.03225799476233484, "acc_norm": 0.30049261083743845, "acc_norm_stderr": 0.03225799476233484 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.04229525846816508, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816508 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.296969696969697, "acc_stderr": 0.03567969772268049, "acc_norm": 0.296969696969697, "acc_norm_stderr": 0.03567969772268049 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2777777777777778, "acc_stderr": 0.03191178226713547, "acc_norm": 0.2777777777777778, "acc_norm_stderr": 0.03191178226713547 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.24870466321243523, "acc_stderr": 0.031195840877700307, "acc_norm": 0.24870466321243523, "acc_norm_stderr": 0.031195840877700307 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.2205128205128205, "acc_stderr": 0.021020672680827912, "acc_norm": 0.2205128205128205, "acc_norm_stderr": 0.021020672680827912 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.24814814814814815, "acc_stderr": 0.0263357394040558, "acc_norm": 0.24814814814814815,
