open-llm-leaderboard-old/details_Isotonic__TinyMixtral-4x248M-MoE
收藏数据集概述
数据集简介
该数据集是在评估模型 Isotonic/TinyMixtral-4x248M-MoE 在 Open LLM Leaderboard 上的自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。
数据集结构
数据集由 1 次运行创建，每个运行可以在每个配置中找到特定的拆分，拆分名称使用运行的时间戳。"train" 拆分始终指向最新的结果。
额外配置
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_Isotonic__TinyMixtral-4x248M-MoE", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-08T22:20:25.743847 运行的最新结果：
python { "all": { "acc": 0.25062534015174737, "acc_stderr": 0.030703691746189168, "acc_norm": 0.25194345598726114, "acc_norm_stderr": 0.03152544108870022, "mc1": 0.23623011015911874, "mc1_stderr": 0.014869755015871093, "mc2": 0.483038971320109, "mc2_stderr": 0.01652857847450844 }, "harness|arc:challenge|25": { "acc": 0.21075085324232082, "acc_stderr": 0.01191827175485218, "acc_norm": 0.27474402730375425, "acc_norm_stderr": 0.013044617212771227 }, "harness|hellaswag|10": { "acc": 0.2548297151961761, "acc_stderr": 0.004348748730529936, "acc_norm": 0.25433180641306513, "acc_norm_stderr": 0.004345949382382375 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909284, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909284 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04072314811876837, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04072314811876837 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.18421052631578946, "acc_stderr": 0.0315469804508223, "acc_norm": 0.18421052631578946, "acc_norm_stderr": 0.0315469804508223 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.23, "acc_stderr": 0.04229525846816506, "acc_norm": 0.23, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.27169811320754716, "acc_stderr": 0.027377706624670713, "acc_norm": 0.27169811320754716, "acc_norm_stderr": 0.027377706624670713 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2361111111111111, "acc_stderr": 0.03551446610810826, "acc_norm": 0.2361111111111111, "acc_norm_stderr": 0.03551446610810826 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.2, "acc_stderr": 0.04020151261036845, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036845 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.26, "acc_stderr": 0.0440844002276808, "acc_norm": 0.26, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.28, "acc_stderr": 0.045126085985421276, "acc_norm": 0.28, "acc_norm_stderr": 0.045126085985421276 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.2543352601156069, "acc_stderr": 0.0332055644308557, "acc_norm": 0.2543352601156069, "acc_norm_stderr": 0.0332055644308557 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.21568627450980393, "acc_stderr": 0.04092563958237654, "acc_norm": 0.21568627450980393, "acc_norm_stderr": 0.04092563958237654 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.27, "acc_stderr": 0.044619604333847415, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847415 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28085106382978725, "acc_stderr": 0.02937917046412482, "acc_norm": 0.28085106382978725, "acc_norm_stderr": 0.02937917046412482 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2894736842105263, "acc_stderr": 0.04266339443159394, "acc_norm": 0.2894736842105263, "acc_norm_stderr": 0.04266339443159394 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.2482758620689655, "acc_stderr": 0.036001056927277716, "acc_norm": 0.2482758620689655, "acc_norm_stderr": 0.036001056927277716 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2222222222222222, "acc_stderr": 0.021411684393694196, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.021411684393694196 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.25396825396825395, "acc_stderr": 0.03893259610604671, "acc_norm": 0.25396825396825395, "acc_norm_stderr": 0.03893259610604671 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.18064516129032257, "acc_stderr": 0.021886178567172548, "acc_norm": 0.18064516129032257, "acc_norm_stderr": 0.021886178567172548 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.27586206896551724, "acc_stderr": 0.031447125816782405, "acc_norm": 0.27586206896551724, "acc_norm_stderr": 0.031447125816782405 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.23, "acc_stderr": 0.042295258468165065, "acc_norm": 0.23, "acc_norm_stderr": 0.042295258468165065 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.25757575757575757, "acc_stderr": 0.03115626951964684, "acc_norm": 0.25757575757575757, "acc_norm_stderr": 0.03115626951964684 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.18134715025906736, "acc_stderr": 0.02780703236068609, "acc_norm": 0.18134715025906736, "acc_norm_stderr": 0.02780703236068609 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.20256410256410257, "acc_stderr": 0.02037766097037138, "acc_norm": 0.20256410256410257, "acc_norm_stderr": 0.02037766097037138 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340492, "acc
