open-llm-leaderboard-old/details_pansophic__gemma-2b-sft-preview
收藏数据集概述
数据集组成
- 该数据集包含63个配置，每个配置对应一个评估任务。
- 数据集由1次运行创建，每个运行的详细结果存储在特定的分割中，分割名称使用运行的时间戳。
- "train"分割始终指向最新的结果。
附加配置
- 一个名为"results"的附加配置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_pansophic__gemma-2b-sft-preview", "harness_winogrande_5", split="train")
最新结果
- 以下是2024-04-09T23:16:38.946597运行的最新结果：
python { "all": { "acc": 0.4624553729893626, "acc_stderr": 0.03462116818721113, "acc_norm": 0.4641211468417102, "acc_norm_stderr": 0.03533344814018203, "mc1": 0.31456548347613217, "mc1_stderr": 0.016255241993179195, "mc2": 0.5129562556405232, "mc2_stderr": 0.014894806809363713 }, "harness|arc:challenge|25": { "acc": 0.49573378839590443, "acc_stderr": 0.014610858923956948, "acc_norm": 0.523037542662116, "acc_norm_stderr": 0.014595873205358269 }, "harness|hellaswag|10": { "acc": 0.5339573790081658, "acc_stderr": 0.004978260641742202, "acc_norm": 0.7360087631945827, "acc_norm_stderr": 0.004398937225038411 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768081, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4, "acc_stderr": 0.04232073695151589, "acc_norm": 0.4, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04046336883978251, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04046336883978251 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.4981132075471698, "acc_stderr": 0.030772653642075664, "acc_norm": 0.4981132075471698, "acc_norm_stderr": 0.030772653642075664 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.4930555555555556, "acc_stderr": 0.04180806750294938, "acc_norm": 0.4930555555555556, "acc_norm_stderr": 0.04180806750294938 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.4161849710982659, "acc_stderr": 0.03758517775404948, "acc_norm": 0.4161849710982659, "acc_norm_stderr": 0.03758517775404948 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.24509803921568626, "acc_stderr": 0.042801058373643966, "acc_norm": 0.24509803921568626, "acc_norm_stderr": 0.042801058373643966 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.43829787234042555, "acc_stderr": 0.032436186361081004, "acc_norm": 0.43829787234042555, "acc_norm_stderr": 0.032436186361081004 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.04372748290278007, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.04372748290278007 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5103448275862069, "acc_stderr": 0.04165774775728763, "acc_norm": 0.5103448275862069, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.328042328042328, "acc_stderr": 0.024180497164376886, "acc_norm": 0.328042328042328, "acc_norm_stderr": 0.024180497164376886 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.35714285714285715, "acc_stderr": 0.04285714285714281, "acc_norm": 0.35714285714285715, "acc_norm_stderr": 0.04285714285714281 }, "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": 0.5193548387096775, "acc_stderr": 0.028422687404312107, "acc_norm": 0.5193548387096775, "acc_norm_stderr": 0.028422687404312107 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.458128078817734, "acc_stderr": 0.03505630140785741, "acc_norm": 0.458128078817734, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6363636363636364, "acc_stderr": 0.03756335775187898, "acc_norm": 0.6363636363636364, "acc_norm_stderr": 0.03756335775187898 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.5858585858585859, "acc_stderr": 0.03509438348879628, "acc_norm": 0.5858585858585859, "acc_norm_stderr": 0.03509438348879628 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.616580310880829, "acc_stderr": 0.03508984236295342, "acc_norm": 0.616580310880829, "acc_norm_stderr": 0.03508984236295342 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.4076923076923077, "acc_stderr": 0.02491524398598784, "acc_norm": 0.4076923076923077, "acc_norm_stderr": 0.02491524398598784 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.28888888888888886, "acc_stderr": 0.027634907264178544, "acc_norm": 0.28888888888888886, "acc_norm_stderr": 0.027634907264178544 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.4327731092436975, "acc_stderr": 0.03218358107742613, "acc_norm": 0.4327731092436975, "acc_norm_stderr": 0.03218358107742
