open-llm-leaderboard-old/details_GritLM__GritLM-8x7B

该数据集是在Open LLM Leaderboard上对GritLM/GritLM-8x7B模型进行评估时自动创建的。数据集由63个配置组成，每个配置对应一个被评估的任务。数据集是从2次运行中创建的，每次运行在每个配置中表示为特定的分割。train分割始终指向最新的结果。一个名为results的额外配置存储了所有运行的聚合结果，这些结果用于计算和显示Open LLM Leaderboard上的聚合指标。README还提供了一个示例，展示了如何使用`datasets`库中的`load_dataset`函数加载运行中的详细信息。

原始信息汇总

数据集概述

该数据集是在对模型 GritLM/GritLM-8x7B 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。
• 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_GritLM__GritLM-8x7B", "harness_winogrande_5", split="train")

最新结果

以下是 2024-03-10T14:24:41.959625 运行的最新结果：

python { "all": { "acc": 0.7125539724588248, "acc_stderr": 0.0303257615066163, "acc_norm": 0.7161704881482764, "acc_norm_stderr": 0.030919401183717173, "mc1": 0.33659730722154224, "mc1_stderr": 0.016542412809494884, "mc2": 0.4947094775859723, "mc2_stderr": 0.014373065476642853 }, "harness|arc:challenge|25": { "acc": 0.6450511945392492, "acc_stderr": 0.013983036904094085, "acc_norm": 0.6774744027303754, "acc_norm_stderr": 0.01365998089427737 }, "harness|hellaswag|10": { "acc": 0.6650069707229636, "acc_stderr": 0.004710234188047369, "acc_norm": 0.865166301533559, "acc_norm_stderr": 0.003408478333768264 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.674074074074074, "acc_stderr": 0.040491220417025055, "acc_norm": 0.674074074074074, "acc_norm_stderr": 0.040491220417025055 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8223684210526315, "acc_stderr": 0.031103182383123384, "acc_norm": 0.8223684210526315, "acc_norm_stderr": 0.031103182383123384 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7962264150943397, "acc_stderr": 0.024790784501775402, "acc_norm": 0.7962264150943397, "acc_norm_stderr": 0.024790784501775402 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.03216600808802268, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.03216600808802268 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.0349610148119118, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.0349610148119118 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.81, "acc_stderr": 0.039427724440366234, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366234 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6851063829787234, "acc_stderr": 0.030363582197238174, "acc_norm": 0.6851063829787234, "acc_norm_stderr": 0.030363582197238174 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6228070175438597, "acc_stderr": 0.04559522141958216, "acc_norm": 0.6228070175438597, "acc_norm_stderr": 0.04559522141958216 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6413793103448275, "acc_stderr": 0.03996629574876719, "acc_norm": 0.6413793103448275, "acc_norm_stderr": 0.03996629574876719 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4947089947089947, "acc_stderr": 0.02574986828855657, "acc_norm": 0.4947089947089947, "acc_norm_stderr": 0.02574986828855657 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.6031746031746031, "acc_stderr": 0.0437588849272706, "acc_norm": 0.6031746031746031, "acc_norm_stderr": 0.0437588849272706 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8387096774193549, "acc_stderr": 0.020923327006423298, "acc_norm": 0.8387096774193549, "acc_norm_stderr": 0.020923327006423298 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6059113300492611, "acc_stderr": 0.034381579670365446, "acc_norm": 0.6059113300492611, "acc_norm_stderr": 0.034381579670365446 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.031922715695483016, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.031922715695483016 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8484848484848485, "acc_stderr": 0.02554565042660362, "acc_norm": 0.8484848484848485, "acc_norm_stderr": 0.02554565042660362 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9430051813471503, "acc_stderr": 0.01673108529360755, "acc_norm": 0.9430051813471503, "acc_norm_stderr": 0.01673108529360755 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7076923076923077, "acc_stderr": 0.023060438380857737, "acc_norm": 0.7076923076923077, "acc_norm_stderr": 0.023060438380857737 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.029670906124630886, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.02967090612

搜集汇总

背景与挑战

背景概述

该数据集是GritLM/GritLM-8x7B模型在Open LLM Leaderboard上的评估结果集合，自动生成并包含63个任务配置，每个配置对应不同的评估任务。数据集基于2次运行，结果以时间戳分割，提供了详细的性能指标如准确率，可用于模型性能分析和比较。