open-llm-leaderboard-old/details_princeton-nlp__Sheared-LLaMA-2.7B-ShareGPT

该数据集是在Open LLM Leaderboard上对模型princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT进行评估时自动创建的。数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为特定配置中的一个分割，分割名称使用运行的时间戳。train分割始终指向最新结果。此外，还有一个名为results的配置存储了所有运行的聚合结果，用于在Open LLM Leaderboard上计算和显示聚合指标。

原始信息汇总

数据集概述

该数据集是在对模型 princeton-nlp/Sheared-LLaMA-2.7B-ShareGPT 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

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。每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
• "train" 分片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_princeton-nlp__Sheared-LLaMA-2.7B-ShareGPT", "harness_winogrande_5", split="train")

最新结果

以下是 2024-01-05T12:10:45.462405 运行的最新结果：

python { "all": { "acc": 0.2919655714473898, "acc_stderr": 0.0318639028810806, "acc_norm": 0.2944023668702236, "acc_norm_stderr": 0.032711391877200874, "mc1": 0.3011015911872705, "mc1_stderr": 0.01605899902610062, "mc2": 0.4771392382771529, "mc2_stderr": 0.015567072294317703 }, "harness|arc:challenge|25": { "acc": 0.3779863481228669, "acc_stderr": 0.014169664520303101, "acc_norm": 0.4104095563139932, "acc_norm_stderr": 0.014374922192642666 }, "harness|hellaswag|10": { "acc": 0.5435172276438957, "acc_stderr": 0.00497084669755231, "acc_norm": 0.7126070503883688, "acc_norm_stderr": 0.004516215206715344 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.23, "acc_stderr": 0.04229525846816505, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816505 }, "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": 0.32894736842105265, "acc_stderr": 0.03823428969926604, "acc_norm": 0.32894736842105265, "acc_norm_stderr": 0.03823428969926604 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.27, "acc_stderr": 0.04461960433384739, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.33584905660377357, "acc_stderr": 0.02906722014664483, "acc_norm": 0.33584905660377357, "acc_norm_stderr": 0.02906722014664483 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2569444444444444, "acc_stderr": 0.03653946969442099, "acc_norm": 0.2569444444444444, "acc_norm_stderr": 0.03653946969442099 }, "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": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.24277456647398843, "acc_stderr": 0.0326926380614177, "acc_norm": 0.24277456647398843, "acc_norm_stderr": 0.0326926380614177 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.16666666666666666, "acc_stderr": 0.03708284662416545, "acc_norm": 0.16666666666666666, "acc_norm_stderr": 0.03708284662416545 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.2297872340425532, "acc_stderr": 0.027501752944412417, "acc_norm": 0.2297872340425532, "acc_norm_stderr": 0.027501752944412417 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489362, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489362 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2827586206896552, "acc_stderr": 0.03752833958003336, "acc_norm": 0.2827586206896552, "acc_norm_stderr": 0.03752833958003336 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.25925925925925924, "acc_stderr": 0.022569897074918424, "acc_norm": 0.25925925925925924, "acc_norm_stderr": 0.022569897074918424 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.2222222222222222, "acc_stderr": 0.037184890068181146, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.037184890068181146 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.04560480215720683, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720683 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.2967741935483871, "acc_stderr": 0.0259885007924119, "acc_norm": 0.2967741935483871, "acc_norm_stderr": 0.0259885007924119 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.2315270935960591, "acc_stderr": 0.029678333141444444, "acc_norm": 0.2315270935960591, "acc_norm_stderr": 0.029678333141444444 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.3393939393939394, "acc_stderr": 0.03697442205031595, "acc_norm": 0.3393939393939394, "acc_norm_stderr": 0.03697442205031595 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25252525252525254, "acc_stderr": 0.030954055470365897, "acc_norm": 0.25252525252525254, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.37305699481865284, "acc_stderr": 0.03490205592048574, "acc_norm": 0.37305699481865284, "acc_norm_stderr": 0.03490205592048574 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.29743589743589743, "acc_stderr": 0.02317740813146593, "acc_norm": 0.29743589743589743, "acc_norm_stderr": 0.02317740813146593 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.02696242432507383, "acc_norm": 0.26666666666666666, "acc