open-llm-leaderboard-old/details_Locutusque__SlimHercules-4.0-Mistral-7B-v0.2
收藏数据集概述
该数据集是在对模型 Locutusque/SlimHercules-4.0-Mistral-7B-v0.2 进行评估运行期间自动创建的，评估运行在 Open LLM Leaderboard 上进行。
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，每次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。
- 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_Locutusque__SlimHercules-4.0-Mistral-7B-v0.2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-15T14:46:29.497498 运行的最新结果：
python { "all": { "acc": 0.6258811997664652, "acc_stderr": 0.032450560325242114, "acc_norm": 0.6297976109556077, "acc_norm_stderr": 0.033104935238970755, "mc1": 0.31334149326805383, "mc1_stderr": 0.016238065069059608, "mc2": 0.453335051403178, "mc2_stderr": 0.01464962524455778 }, "harness|arc:challenge|25": { "acc": 0.5733788395904437, "acc_stderr": 0.014453185592920295, "acc_norm": 0.6006825938566553, "acc_norm_stderr": 0.01431209455794671 }, "harness|hellaswag|10": { "acc": 0.6344353714399522, "acc_stderr": 0.004806039039008959, "acc_norm": 0.8353913563035252, "acc_norm_stderr": 0.003700690995600888 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "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": 0.6513157894736842, "acc_stderr": 0.03878139888797611, "acc_norm": 0.6513157894736842, "acc_norm_stderr": 0.03878139888797611 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.02914690474779833, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.02914690474779833 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "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": 0.51, "acc_stderr": 0.05024183937956911, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6358381502890174, "acc_stderr": 0.03669072477416907, "acc_norm": 0.6358381502890174, "acc_norm_stderr": 0.03669072477416907 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04690650298201942, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04690650298201942 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.4649122807017544, "acc_stderr": 0.046920083813689104, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.046920083813689104 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4126984126984127, "acc_stderr": 0.02535574126305527, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.02535574126305527 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.04444444444444449, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.32, "acc_stderr": 0.04688261722621504, "acc_norm": 0.32, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7290322580645161, "acc_stderr": 0.025284416114900156, "acc_norm": 0.7290322580645161, "acc_norm_stderr": 0.025284416114900156 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.03256866661681102, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7828282828282829, "acc_stderr": 0.02937661648494562, "acc_norm": 0.7828282828282829, "acc_norm_stderr": 0.02937661648494562 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758723, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758723 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6230769230769231, "acc_stderr": 0.024570975364225995, "acc_norm": 0.6230769230769231, "acc_norm_stderr": 0.024570975364225995 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.028226446749683515, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.028226446749683515 },
