open-llm-leaderboard-old/details_one-man-army__una-neural-chat-v3-3-P2-OMA
收藏数据集概述
该数据集是在模型one-man-army/una-neural-chat-v3-3-P2-OMA在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
- 数据集包含63个配置，每个配置对应一个评估任务。
- 数据集从2次运行中创建，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train"分片始终指向最新的结果。
- 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_one-man-army__una-neural-chat-v3-3-P2-OMA", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-13T14:25:29.170115运行的最新结果：
python { "all": { "acc": 0.6348474564429509, "acc_stderr": 0.032547874322213524, "acc_norm": 0.6360060797642175, "acc_norm_stderr": 0.03320713700726099, "mc1": 0.4883720930232558, "mc1_stderr": 0.017498767175740088, "mc2": 0.6548761858136044, "mc2_stderr": 0.01508528563797577 }, "harness|arc:challenge|25": { "acc": 0.6390784982935154, "acc_stderr": 0.014034761386175456, "acc_norm": 0.6732081911262798, "acc_norm_stderr": 0.013706665975587331 }, "harness|hellaswag|10": { "acc": 0.6783509261103365, "acc_stderr": 0.004661544991583035, "acc_norm": 0.8632742481577375, "acc_norm_stderr": 0.00342855459595022 }, "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": 0.6222222222222222, "acc_stderr": 0.04188307537595852, "acc_norm": 0.6222222222222222, "acc_norm_stderr": 0.04188307537595852 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.03860731599316092, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316092 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "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": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "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": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "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": 0.43137254901960786, "acc_stderr": 0.04928099597287534, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287534 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.045126085985421276, "acc_norm": 0.72, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.032500536843658404, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.032500536843658404 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4649122807017544, "acc_stderr": 0.04692008381368909, "acc_norm": 0.4649122807017544, "acc_norm_stderr": 0.04692008381368909 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.025075981767601688, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.025075981767601688 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7548387096774194, "acc_stderr": 0.024472243840895514, "acc_norm": 0.7548387096774194, "acc_norm_stderr": 0.024472243840895514 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.035025446508458714, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.035025446508458714 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "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": 0.797979797979798, "acc_stderr": 0.028606204289229872, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.028606204289229872 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121427, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121427 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6358974358974359, "acc_stderr": 0.02439667298509477, "acc_norm": 0.6358974358974359, "acc_norm_stderr": 0.02439667298509477 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083015, "acc_norm
