open-llm-leaderboard-old/details_migtissera__Synthia-v3.0-11B
收藏数据集概述
该数据集是在对模型 migtissera/Synthia-v3.0-11B 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 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，每个运行可以在每个配置中找到特定的分割，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_migtissera__Synthia-v3.0-11B", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-29T16:55:08.387804 运行的最新结果：
python { "all": { "acc": 0.6619770657414235, "acc_stderr": 0.031604834430978876, "acc_norm": 0.6646447644378076, "acc_norm_stderr": 0.03224520098122884, "mc1": 0.32802937576499386, "mc1_stderr": 0.01643563293281503, "mc2": 0.48221845296383764, "mc2_stderr": 0.014644551274990076 }, "harness|arc:challenge|25": { "acc": 0.5955631399317406, "acc_stderr": 0.014342036483436177, "acc_norm": 0.6407849829351536, "acc_norm_stderr": 0.014020224155839159 }, "harness|hellaswag|10": { "acc": 0.6618203545110536, "acc_stderr": 0.004721231637092722, "acc_norm": 0.8532164907388966, "acc_norm_stderr": 0.0035316671852358337 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.75, "acc_stderr": 0.03523807393012047, "acc_norm": 0.75, "acc_norm_stderr": 0.03523807393012047 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322666, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322666 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.034765901043041336, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.034765901043041336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620333, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.57, "acc_stderr": 0.04975698519562428, "acc_norm": 0.57, "acc_norm_stderr": 0.04975698519562428 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6878612716763006, "acc_stderr": 0.035331333893236574, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.035331333893236574 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.048786087144669955, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "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": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6206896551724138, "acc_stderr": 0.040434618619167466, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.040434618619167466 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.46296296296296297, "acc_stderr": 0.02568056464005688, "acc_norm": 0.46296296296296297, "acc_norm_stderr": 0.02568056464005688 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.044444444444444495, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.044444444444444495 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8064516129032258, "acc_stderr": 0.022475258525536057, "acc_norm": 0.8064516129032258, "acc_norm_stderr": 0.022475258525536057 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.035179450386910616, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.035179450386910616 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8121212121212121, "acc_stderr": 0.03050193405942914, "acc_norm": 0.8121212121212121, "acc_norm_stderr": 0.03050193405942914 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.024825909793343343, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.024825909793343343 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9222797927461139, "acc_stderr": 0.01932180555722315, "acc_norm": 0.9222797927461139, "acc_norm_stderr": 0.01932180555722315 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.023946724741563976, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.023946724741563976 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.029670906124630882, "acc_norm": 0.3851851851851852, "acc_norm_stderr": 0.02967090
