open-llm-leaderboard-old/details_ChuckMcSneed__Gembo-v1.1-70b
收藏数据集概述
数据集简介
该数据集是在模型 ChuckMcSneed/Gembo-v1.1-70b 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集结构
- 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 1 次运行中创建，每次运行可以在每个配置中找到一个特定的分割，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置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_ChuckMcSneed__Gembo-v1.1-70b", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自 2024-02-10T16:28:59.613230 的运行： python { "all": { "acc": 0.7037169866635749, "acc_stderr": 0.030408999256517827, "acc_norm": 0.7091585136665425, "acc_norm_stderr": 0.030988155888902767, "mc1": 0.4455324357405141, "mc1_stderr": 0.017399335280140354, "mc2": 0.6245089770845819, "mc2_stderr": 0.01502641583909722 }, "harness|arc:challenge|25": { "acc": 0.6715017064846417, "acc_stderr": 0.013724978465537302, "acc_norm": 0.7098976109215017, "acc_norm_stderr": 0.013261573677520764 }, "harness|hellaswag|10": { "acc": 0.6822346146186019, "acc_stderr": 0.004646561453031608, "acc_norm": 0.8689504082852022, "acc_norm_stderr": 0.003367649220362108 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7828947368421053, "acc_stderr": 0.03355045304882924, "acc_norm": 0.7828947368421053, "acc_norm_stderr": 0.03355045304882924 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.74, "acc_stderr": 0.04408440022768081, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768081 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.720754716981132, "acc_stderr": 0.027611163402399715, "acc_norm": 0.720754716981132, "acc_norm_stderr": 0.027611163402399715 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8194444444444444, "acc_stderr": 0.032166008088022675, "acc_norm": 0.8194444444444444, "acc_norm_stderr": 0.032166008088022675 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.036430371689585475, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.036430371689585475 }, "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": 0.79, "acc_stderr": 0.04093601807403326, "acc_norm": 0.79, "acc_norm_stderr": 0.04093601807403326 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6680851063829787, "acc_stderr": 0.030783736757745653, "acc_norm": 0.6680851063829787, "acc_norm_stderr": 0.030783736757745653 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.0470070803355104, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.0470070803355104 }, "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": 0.48677248677248675, "acc_stderr": 0.025742297289575142, "acc_norm": 0.48677248677248675, "acc_norm_stderr": 0.025742297289575142 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5, "acc_stderr": 0.04472135954999579, "acc_norm": 0.5, "acc_norm_stderr": 0.04472135954999579 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "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": 0.541871921182266, "acc_stderr": 0.03505630140785741, "acc_norm": 0.541871921182266, "acc_norm_stderr": 0.03505630140785741 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8363636363636363, "acc_stderr": 0.02888787239548795, "acc_norm": 0.8363636363636363, "acc_norm_stderr": 0.02888787239548795 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.898989898989899, "acc_stderr": 0.021469735576055343, "acc_norm": 0.898989898989899, "acc_norm_stderr": 0.021469735576055343 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9326424870466321, "acc_stderr": 0.018088393839078894, "acc_norm": 0.9326424870466321, "acc_norm_stderr": 0.018088393839078894 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7282051282051282, "acc_stderr": 0.022556551010132368, "acc_norm": 0.7282051282051282, "acc_norm_stderr": 0.022556551010132368 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.32592592592592595, "acc_stderr": 0.028578348365473072, "acc_norm": 0.32592592592592595, "acc_norm_stderr": 0.028578348365473072 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.773109243697479, "acc_stderr": 0.027205371538279472, "acc_norm": 0.7731092
