open-llm-leaderboard-old/details_Weyaxi__TekniumAiroboros-Nebula-7B
收藏数据集概述
数据集简介
该数据集是在模型 Weyaxi/TekniumAiroboros-Nebula-7B 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
- 该数据集包含 64 个配置，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找到特定的拆分，拆分名称使用运行的时间戳。
- "train" 拆分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_Weyaxi__TekniumAiroboros-Nebula-7B_public", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2023-11-08T17:19:18.874101 的运行： python { "all": { "acc": 0.5486392579762343, "acc_stderr": 0.03374349666110138, "acc_norm": 0.5573176954338681, "acc_norm_stderr": 0.03452133425560909, "mc1": 0.34761321909424725, "mc1_stderr": 0.016670769188897303, "mc2": 0.5163563481502564, "mc2_stderr": 0.015552871980185646, "em": 0.34721057046979864, "em_stderr": 0.004875539476141144, "f1": 0.4132676174496653, "f1_stderr": 0.004730745670924258 }, "harness|arc:challenge|25": { "acc": 0.5264505119453925, "acc_stderr": 0.01459093135812017, "acc_norm": 0.5716723549488054, "acc_norm_stderr": 0.014460496367599019 }, "harness|hellaswag|10": { "acc": 0.6211909978092014, "acc_stderr": 0.004840990593494692, "acc_norm": 0.817167894841665, "acc_norm_stderr": 0.0038573886135331004 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5131578947368421, "acc_stderr": 0.04067533136309174, "acc_norm": 0.5131578947368421, "acc_norm_stderr": 0.04067533136309174 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6075471698113207, "acc_stderr": 0.030052580579557845, "acc_norm": 0.6075471698113207, "acc_norm_stderr": 0.030052580579557845 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.039812405437178615, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.34, "acc_stderr": 0.047609522856952344, "acc_norm": 0.34, "acc_norm_stderr": 0.047609522856952344 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5202312138728323, "acc_stderr": 0.03809342081273958, "acc_norm": 0.5202312138728323, "acc_norm_stderr": 0.03809342081273958 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.2647058823529412, "acc_stderr": 0.04389869956808777, "acc_norm": 0.2647058823529412, "acc_norm_stderr": 0.04389869956808777 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5148936170212766, "acc_stderr": 0.032671518489247764, "acc_norm": 0.5148936170212766, "acc_norm_stderr": 0.032671518489247764 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4896551724137931, "acc_stderr": 0.04165774775728763, "acc_norm": 0.4896551724137931, "acc_norm_stderr": 0.04165774775728763 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.36772486772486773, "acc_stderr": 0.024833839825562427, "acc_norm": 0.36772486772486773, "acc_norm_stderr": 0.024833839825562427 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377563, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377563 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6548387096774193, "acc_stderr": 0.02704574657353433, "acc_norm": 0.6548387096774193, "acc_norm_stderr": 0.02704574657353433 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.3793103448275862, "acc_stderr": 0.034139638059062345, "acc_norm": 0.3793103448275862, "acc_norm_stderr": 0.034139638059062345 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7212121212121212, "acc_stderr": 0.03501438706296781, "acc_norm": 0.7212121212121212, "acc_norm_stderr": 0.03501438706296781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7272727272727273, "acc_stderr": 0.03173071239071724, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.03173071239071724 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7823834196891192, "acc_stderr": 0.029778663037752954, "acc_norm": 0.7823834196891192, "acc_norm_stderr": 0.029778663037752954 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5333333333333333, "acc_stderr": 0.02529460802398647, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.02529460802398647 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_
