open-llm-leaderboard-old/details_Cartinoe5930__Llama2_init_Mistral
收藏数据集概述
该数据集是在对模型 Cartinoe5930/Llama2_init_Mistral 进行评估运行期间自动创建的，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作为一个特定的分割找到，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。
最新结果
以下是 2024-01-17T03:13:02.532264 运行的最新结果：
python { "all": { "acc": 0.6375746321703655, "acc_stderr": 0.03225546197812389, "acc_norm": 0.6434618962614028, "acc_norm_stderr": 0.032904960223920136, "mc1": 0.2802937576499388, "mc1_stderr": 0.015723139524608763, "mc2": 0.4215137349816427, "mc2_stderr": 0.014137575959685471 }, "harness|arc:challenge|25": { "acc": 0.5691126279863481, "acc_stderr": 0.014471133392642476, "acc_norm": 0.6006825938566553, "acc_norm_stderr": 0.014312094557946709 }, "harness|hellaswag|10": { "acc": 0.629555865365465, "acc_stderr": 0.004819367172685962, "acc_norm": 0.8330013941445927, "acc_norm_stderr": 0.0037221237096104645 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.27, "acc_stderr": 0.04461960433384741, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384741 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.03860731599316091, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316091 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322663, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322663 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7291666666666666, "acc_stderr": 0.03716177437566017, "acc_norm": 0.7291666666666666, "acc_norm_stderr": 0.03716177437566017 }, "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": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.03614665424180826, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.03614665424180826 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.042295258468165065, "acc_norm": 0.77, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.574468085106383, "acc_stderr": 0.03232146916224468, "acc_norm": 0.574468085106383, "acc_norm_stderr": 0.03232146916224468 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5724137931034483, "acc_stderr": 0.04122737111370332, "acc_norm": 0.5724137931034483, "acc_norm_stderr": 0.04122737111370332 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37566137566137564, "acc_stderr": 0.024942368931159795, "acc_norm": 0.37566137566137564, "acc_norm_stderr": 0.024942368931159795 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768177, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768177 }, "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": 0.7709677419354839, "acc_stderr": 0.023904914311782648, "acc_norm": 0.7709677419354839, "acc_norm_stderr": 0.023904914311782648 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5270935960591133, "acc_stderr": 0.03512819077876106, "acc_norm": 0.5270935960591133, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621504, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621504 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7818181818181819, "acc_stderr": 0.032250781083062896, "acc_norm": 0.7818181818181819, "acc_norm_stderr": 0.032250781083062896 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.029857515673386417, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.029857515673386417 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8652849740932642, "acc_stderr": 0.02463978909770944, "acc_norm": 0.8652849740932642, "acc_norm_stderr": 0.02463978909770944 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.023901157979402534, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.023901157979402534 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.028820884666253255, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.028820884666253255 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6596638655462185, "acc_stderr": 0.0307780574229
