open-llm-leaderboard-old/details_jpquiroga__Mistral_7B_slerp_merge_instruct_open_orca
收藏数据集概述
数据集摘要
该数据集是在模型 jpquiroga/Mistral_7B_slerp_merge_instruct_open_orca 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
数据集组成
- 数据集由 63 个配置组成，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一个特定的拆分，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，用于计算并在 Open LLM Leaderboard 上显示聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jpquiroga__Mistral_7B_slerp_merge_instruct_open_orca", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-16T10:47:33.311388 运行的最新结果：
python { "all": { "acc": 0.6161554493970413, "acc_stderr": 0.032936724283737305, "acc_norm": 0.6211432753839832, "acc_norm_stderr": 0.033602576002331234, "mc1": 0.40269277845777235, "mc1_stderr": 0.01716883093518722, "mc2": 0.5634809148432152, "mc2_stderr": 0.015447882111793024 }, "harness|arc:challenge|25": { "acc": 0.5810580204778157, "acc_stderr": 0.014418106953639013, "acc_norm": 0.6262798634812287, "acc_norm_stderr": 0.014137708601759091 }, "harness|hellaswag|10": { "acc": 0.6211909978092014, "acc_stderr": 0.004840990593494689, "acc_norm": 0.8169687313284206, "acc_norm_stderr": 0.0038590186619620053 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.03894734487013316, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.03894734487013316 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880267, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880267 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.037038511930995215, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.037038511930995215 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.35294117647058826, "acc_stderr": 0.047551296160629475, "acc_norm": 0.35294117647058826, "acc_norm_stderr": 0.047551296160629475 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5234042553191489, "acc_stderr": 0.032650194750335815, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.032650194750335815 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.04630653203366596, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.04630653203366596 }, "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": 0.4021164021164021, "acc_stderr": 0.02525303255499769, "acc_norm": 0.4021164021164021, "acc_norm_stderr": 0.02525303255499769 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377562, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377562 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7354838709677419, "acc_stderr": 0.02509189237885928, "acc_norm": 0.7354838709677419, "acc_norm_stderr": 0.02509189237885928 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145632, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145632 }, "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": 0.7777777777777778, "acc_stderr": 0.029620227874790486, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.029620227874790486 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8290155440414507, "acc_stderr": 0.027171213683164542, "acc_norm": 0.8290155440414507, "acc_norm_stderr": 0.027171213683164542 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6051282051282051, "acc_stderr": 0.024784316942156395, "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.024784316942156395 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.028406533090608456, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.0284065330906084
