open-llm-leaderboard-old/details_Charlie911__MultiLora-drop-sharegpt
收藏数据集概述
该数据集是在评估模型 Charlie911/MultiLora-drop-sharegpt 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 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，用于计算和显示在 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_Charlie911__MultiLora-drop-sharegpt", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-01-23T20:13:52.401722：
python { "all": { "acc": 0.4103189833137969, "acc_stderr": 0.034440356205935406, "acc_norm": 0.4152994817197388, "acc_norm_stderr": 0.03526445965091106, "mc1": 0.3047735618115055, "mc1_stderr": 0.016114124156882455, "mc2": 0.44825405044907884, "mc2_stderr": 0.014892271476699756 }, "harness|arc:challenge|25": { "acc": 0.4445392491467577, "acc_stderr": 0.014521226405627077, "acc_norm": 0.4761092150170648, "acc_norm_stderr": 0.014594701798071655 }, "harness|hellaswag|10": { "acc": 0.49302927703644694, "acc_stderr": 0.004989296471157074, "acc_norm": 0.6597291376219877, "acc_norm_stderr": 0.0047283185778352246 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4148148148148148, "acc_stderr": 0.04256193767901407, "acc_norm": 0.4148148148148148, "acc_norm_stderr": 0.04256193767901407 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.40131578947368424, "acc_stderr": 0.039889037033362836, "acc_norm": 0.40131578947368424, "acc_norm_stderr": 0.039889037033362836 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.46037735849056605, "acc_stderr": 0.030676096599389188, "acc_norm": 0.46037735849056605, "acc_norm_stderr": 0.030676096599389188 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.3680555555555556, "acc_stderr": 0.04032999053960718, "acc_norm": 0.3680555555555556, "acc_norm_stderr": 0.04032999053960718 }, "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": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4046242774566474, "acc_stderr": 0.03742461193887248, "acc_norm": 0.4046242774566474, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.23529411764705882, "acc_stderr": 0.04220773659171453, "acc_norm": 0.23529411764705882, "acc_norm_stderr": 0.04220773659171453 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.43829787234042555, "acc_stderr": 0.03243618636108101, "acc_norm": 0.43829787234042555, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.21929824561403508, "acc_stderr": 0.03892431106518754, "acc_norm": 0.21929824561403508, "acc_norm_stderr": 0.03892431106518754 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.33793103448275863, "acc_stderr": 0.0394170763206489, "acc_norm": 0.33793103448275863, "acc_norm_stderr": 0.0394170763206489 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2619047619047619, "acc_stderr": 0.022644212615525214, "acc_norm": 0.2619047619047619, "acc_norm_stderr": 0.022644212615525214 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949098, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949098 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.49032258064516127, "acc_stderr": 0.02843867799890955, "acc_norm": 0.49032258064516127, "acc_norm_stderr": 0.02843867799890955 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.32019704433497537, "acc_stderr": 0.032826493853041504, "acc_norm": 0.32019704433497537, "acc_norm_stderr": 0.032826493853041504 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.46060606060606063, "acc_stderr": 0.03892207016552012, "acc_norm": 0.46060606060606063, "acc_norm_stderr": 0.03892207016552012 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5, "acc_stderr": 0.035623524993954825, "acc_norm": 0.5, "acc_norm_stderr": 0.035623524993954825 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.5233160621761658, "acc_stderr": 0.03604513672442202, "acc_norm": 0.5233160621761658, "acc_norm_stderr": 0.03604513672442202 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.36923076923076925, "acc_stderr": 0.02446861524147891, "acc_norm": 0.36923076923076925, "acc_norm_stderr": 0.02446861524147891 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.027420019350945277, "acc_norm": 0.2814814814814815, "acc_norm_stderr": 0.02742001935
