open-llm-leaderboard-old/details_dddsaty__SOLAR_Merge_Adapter_DPO_Orca
收藏数据集概述
数据集来源
该数据集是在对模型 dddsaty/SOLAR_Merge_Adapter_DPO_Orca 进行评估运行时自动创建的，评估运行在 Open LLM Leaderboard 上进行。
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。数据集是从 1 次运行中创建的，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。
结果配置
一个额外的配置 "results" 存储了所有运行的聚合结果，并用于计算和显示 Open LLM Leaderboard 上的聚合指标。
加载数据示例
要加载某个运行的详细信息，可以使用以下代码： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_dddsaty__SOLAR_Merge_Adapter_DPO_Orca", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-05T08:48:15.938281 运行的最新结果： python { "all": { "acc": 0.6327439375185642, "acc_stderr": 0.032443250608216324, "acc_norm": 0.6355200172658205, "acc_norm_stderr": 0.03310341022715256, "mc1": 0.36107711138310894, "mc1_stderr": 0.016814312844836882, "mc2": 0.51488245253393, "mc2_stderr": 0.015188854393420268 }, "harness|arc:challenge|25": { "acc": 0.6109215017064846, "acc_stderr": 0.014247309976045607, "acc_norm": 0.6390784982935154, "acc_norm_stderr": 0.014034761386175452 }, "harness|hellaswag|10": { "acc": 0.6499701254730134, "acc_stderr": 0.004760041843651493, "acc_norm": 0.8458474407488548, "acc_norm_stderr": 0.0036035695286784114 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.562962962962963, "acc_stderr": 0.04284958639753401, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.04284958639753401 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.65, "acc_stderr": 0.0479372485441102, "acc_norm": 0.65, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.02906722014664483, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.02906722014664483 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03745554791462456, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03745554791462456 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "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": 0.6184971098265896, "acc_stderr": 0.03703851193099522, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099522 }, "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": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5531914893617021, "acc_stderr": 0.0325005368436584, "acc_norm": 0.5531914893617021, "acc_norm_stderr": 0.0325005368436584 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6, "acc_stderr": 0.04082482904638628, "acc_norm": 0.6, "acc_norm_stderr": 0.04082482904638628 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41005291005291006, "acc_stderr": 0.025331202438944423, "acc_norm": 0.41005291005291006, "acc_norm_stderr": 0.025331202438944423 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.04360314860077459, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.04360314860077459 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7322580645161291, "acc_stderr": 0.02518900666021238, "acc_norm": 0.7322580645161291, "acc_norm_stderr": 0.02518900666021238 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.43349753694581283, "acc_stderr": 0.03486731727419872, "acc_norm": 0.43349753694581283, "acc_norm_stderr": 0.03486731727419872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.04852365870939098, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939098 }, "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": 0.8282828282828283, "acc_stderr": 0.0268697161874299, "acc_norm": 0.8282828282828283, "acc_norm_stderr": 0.0268697161874299 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8756476683937824, "acc_stderr": 0.023814477086593566, "acc_norm": 0.8756476683937824, "acc_norm_stderr": 0.023814477086593566 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6076923076923076, "acc_stderr": 0.02475600038213095, "acc_norm": 0.6076923076923076, "acc_norm_stderr": 0.02475600038213095 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3888888888888889, "acc_stderr": 0.029723278961476664, "acc_norm": 0.3888888888888889, "acc_norm_stderr":
