open-llm-leaderboard-old/details_euclaise__Ferret_7B
收藏数据集概述
数据集简介
该数据集是在评估模型 euclaise/Ferret_7B 在 Open LLM Leaderboard 上的运行过程中自动创建的。数据集包含 64 个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：64 个配置
- 数据来源：从 1 次运行中创建
- 数据分割：每个配置包含特定分割，分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置："results" 配置存储所有运行的聚合结果，用于计算和显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_euclaise__Ferret_7B_public", "harness_winogrande_5", split="train")
最新结果
以下是 2023-11-24T20:51:17.073037 运行的最新结果：
python { "all": { "acc": 0.5942716228548698, "acc_stderr": 0.033152282530121875, "acc_norm": 0.6048893408330033, "acc_norm_stderr": 0.03399052086609082, "mc1": 0.2766217870257038, "mc1_stderr": 0.015659605755326923, "mc2": 0.3993660994529629, "mc2_stderr": 0.014553301107110514, "em": 0.001572986577181208, "em_stderr": 0.00040584511324177344, "f1": 0.06532718120805381, "f1_stderr": 0.0014896342146480434 }, "harness|arc:challenge|25": { "acc": 0.5776450511945392, "acc_stderr": 0.014434138713379983, "acc_norm": 0.6228668941979523, "acc_norm_stderr": 0.014163366896192598 }, "harness|hellaswag|10": { "acc": 0.6250746863174667, "acc_stderr": 0.004831142570475506, "acc_norm": 0.8132842063333997, "acc_norm_stderr": 0.0038888680996290764 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6074074074074074, "acc_stderr": 0.0421850621536888, "acc_norm": 0.6074074074074074, "acc_norm_stderr": 0.0421850621536888 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.03860731599316091, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316091 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6566037735849056, "acc_stderr": 0.02922452646912479, "acc_norm": 0.6566037735849056, "acc_norm_stderr": 0.02922452646912479 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.03899073687357335, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.03899073687357335 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "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": 0.5722543352601156, "acc_stderr": 0.03772446857518027, "acc_norm": 0.5722543352601156, "acc_norm_stderr": 0.03772446857518027 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.04560480215720684, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108101, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.047028804320496165, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.047028804320496165 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.593103448275862, "acc_stderr": 0.04093793981266236, "acc_norm": 0.593103448275862, "acc_norm_stderr": 0.04093793981266236 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.025075981767601677, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.025075981767601677 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.0436031486007746, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.0436031486007746 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6774193548387096, "acc_stderr": 0.026593084516572277, "acc_norm": 0.6774193548387096, "acc_norm_stderr": 0.026593084516572277 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.47783251231527096, "acc_stderr": 0.035145285621750094, "acc_norm": 0.47783251231527096, "acc_norm_stderr": 0.035145285621750094 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7474747474747475, "acc_stderr": 0.030954055470365897, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397467, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397467 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5897435897435898, "acc_stderr": 0.024939313906940798, "acc_norm": 0.5897435897435898, "acc_norm_stderr": 0.024939313906940798 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2814814814814815, "acc_stderr": 0.02742
