open-llm-leaderboard/details_Severian__ANIMA-Phi-Neptune-Mistral-7B-v3

该数据集是在评估模型Severian/ANIMA-Phi-Neptune-Mistral-7B-v3时自动创建的，用于在Open LLM Leaderboard上进行评估。数据集包含61个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果存储为特定配置中的一个分割，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置，存储了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。

原始信息汇总

数据集概述

数据集创建背景

该数据集是在对模型 Severian/ANIMA-Phi-Neptune-Mistral-7B-v3 进行评估运行期间自动创建的，评估结果展示在 Open LLM Leaderboard 上。

数据集结构

• 配置数量：数据集包含 61 个配置，每个配置对应一个评估任务。
• 运行次数：数据集来自 1 次运行。每个运行结果作为一个特定的分割（split）存储在每个配置中，分割名称使用运行的时间戳。
• 最新结果："train" 分割始终指向最新的结果。
• 汇总结果：一个额外的配置 "results" 存储所有运行的汇总结果，用于计算和显示在 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_Severian__ANIMA-Phi-Neptune-Mistral-7B-v3", "harness_truthfulqa_mc_0", split="train")

最新结果

以下是 2023-10-11T01:16:32.937269 运行 的最新结果：

python { "all": { "acc": 0.5392786633208031, "acc_stderr": 0.03494779312823446, "acc_norm": 0.5431264898387953, "acc_norm_stderr": 0.03493217150757376, "mc1": 0.412484700122399, "mc1_stderr": 0.01723329939957122, "mc2": 0.5940288949043588, "mc2_stderr": 0.015208554054531144 }, "harness|arc:challenge|25": { "acc": 0.5401023890784983, "acc_stderr": 0.01456431885692485, "acc_norm": 0.568259385665529, "acc_norm_stderr": 0.014474591427196202 }, "harness|hellaswag|10": { "acc": 0.5893248356901015, "acc_stderr": 0.004909509538525159, "acc_norm": 0.7881896036646087, "acc_norm_stderr": 0.004077561349272391 }, "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": 0.4666666666666667, "acc_stderr": 0.043097329010363554, "acc_norm": 0.4666666666666667, "acc_norm_stderr": 0.043097329010363554 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5263157894736842, "acc_stderr": 0.04063302731486671, "acc_norm": 0.5263157894736842, "acc_norm_stderr": 0.04063302731486671 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.55, "acc_stderr": 0.04999999999999999, "acc_norm": 0.55, "acc_norm_stderr": 0.04999999999999999 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6377358490566037, "acc_stderr": 0.0295822451283843, "acc_norm": 0.6377358490566037, "acc_norm_stderr": 0.0295822451283843 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5347222222222222, "acc_stderr": 0.04171115858181618, "acc_norm": 0.5347222222222222, "acc_norm_stderr": 0.04171115858181618 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "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": 0.5722543352601156, "acc_stderr": 0.037724468575180276, "acc_norm": 0.5722543352601156, "acc_norm_stderr": 0.037724468575180276 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.30392156862745096, "acc_stderr": 0.045766654032077615, "acc_norm": 0.30392156862745096, "acc_norm_stderr": 0.045766654032077615 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4425531914893617, "acc_stderr": 0.03246956919789958, "acc_norm": 0.4425531914893617, "acc_norm_stderr": 0.03246956919789958 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.04579639422070435, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.04579639422070435 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3439153439153439, "acc_stderr": 0.024464426625596433, "acc_norm": 0.3439153439153439, "acc_norm_stderr": 0.024464426625596433 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3888888888888889, "acc_stderr": 0.0436031486007746, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.0436031486007746 }, "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": 0.6161290322580645, "acc_stderr": 0.02766618207553965, "acc_norm": 0.6161290322580645, "acc_norm_stderr": 0.02766618207553965 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.37438423645320196, "acc_stderr": 0.03405155380561952, "acc_norm": 0.37438423645320196, "acc_norm_stderr": 0.03405155380561952 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6545454545454545, "acc_stderr": 0.03713158067481913, "acc_norm": 0.6545454545454545, "acc_norm_stderr": 0.03713158067481913 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.6565656565656566, "acc_stderr": 0.03383201223244441, "acc_norm": 0.6565656565656566, "acc_norm_stderr": 0.03383201223244441 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7357512953367875, "acc_stderr": 0.03182155050916645, "acc_norm": 0.7357512953367875, "acc_norm_stderr": 0.03182155050916645 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.47692307692307695, "acc_stderr": 0.025323990861736118, "acc_norm": 0.47692307692307695, "acc_norm_stderr": 0.025323990861736118 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2962962962962963, "acc_stderr": 0.027840811495871937, "acc_norm": 0.2962962962962963, "acc_norm_stderr": 0.027840811495871937 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.4957983193277311, "acc_stderr": 0.0324773433444811, "acc_norm": 0.4957983193277311, "acc_norm_stderr": 0.0324773433444811 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.2781456953642384, "acc_stderr": 0.03658603262763743, "acc_norm": 0.2781456953642384, "acc_norm_stderr": 0.03658603262763743 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.7229357798165138, "acc_stderr": 0.01918848259016953, "acc_norm": 0.7229357798165138, "acc_norm_stderr": 0.01918848259016953 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.39814814814814814, "acc_stderr": 0.033384734032074016, "acc_norm": 0.39814814814814814, "acc_norm_stderr": 0.033384734032074016 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.6519607843137255, "acc_stderr": 0.03343311240488418, "acc_norm": 0.6519607843137255, "acc_norm_stderr": 0.03343311240488418 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7088607594936709, "acc_stderr": 0.02957160106575337, "acc_norm": 0.7088607594936709, "acc_norm_stderr": 0.02957160106575337 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6098654708520179, "acc_stderr": 0.03273766725459157, "acc_norm": 0.6098654708520179, "acc_norm_stderr": 0.03273766725459157 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.6183206106870229, "acc_stderr": 0.0426073515764456, "acc_norm": 0.6183206106870229, "acc_norm_stderr": 0.0426073515764456 }, "harness|hendrycksTest-international_law|5": { "acc": 0.6446280991735537, "acc_stderr": 0.0436923632657398, "acc_norm": 0.6446280991735537, "acc_norm_stderr": 0.0436923632657398 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04712821257426769, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04712821257426769 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.6196319018404908, "acc_stderr": 0.038142698932618374, "acc_norm": 0.6196319018404908, "acc_norm_stderr": 0.038142698932618374 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.39285714285714285, "acc_stderr": 0.04635550135609976, "acc_norm": 0.39285714285714285, "acc_norm_stderr": 0.04635550135609976 }, "harness|hendrycksTest-management|5": { "acc": 0.7184466019417476, "acc_stderr": 0.04453254836326468, "acc_norm": 0.7184466019417476, "acc_norm_stderr": 0.04453254836326468 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8290598290598291, "acc_stderr": 0.024662496845209818, "acc_norm": 0.8290598290598291, "acc_norm_stderr": 0.024662496845209818 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.7088122605363985, "acc_stderr": 0.016246087069701407, "acc_norm": 0.7088122605363985, "acc_norm_stderr": 0.016246087069701407 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.5664739884393064, "acc_stderr": 0.02668013476167922, "acc_norm": 0.5664739884393064, "acc_norm_stderr": 0.02668013476167922 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.34972067039106147, "acc_stderr": 0.015949308790233638, "acc_norm": 0.34972067039106147, "acc_norm_stderr": 0.015949308790233638 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.5686274509803921, "acc_stderr": 0.028358956313423545, "acc_norm": 0.5686274509803921, "acc_norm_stderr": 0.028358956313423545 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.6302250803858521, "acc_stderr": 0.027417996705630998, "acc_norm": 0.6302250803858521, "acc_norm_stderr": 0.027417996705630998 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.6018518518518519, "acc_stderr": 0.027237415094592474, "acc_norm": 0.6018518518518519, "acc_norm_stderr": 0.027237415094592474 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.3723404255319149, "acc_stderr": 0.028838921471251455, "acc_norm": 0.3723404255319149, "acc_norm_stderr": 0.028838921471251455 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.38722294654498046, "acc_stderr": 0.012441155326854927, "acc_norm": 0.38722294654498046, "acc_norm_stderr": 0.012441155326854927 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.4852941176470588, "acc_stderr": 0.03035969707904611, "acc_norm": 0.4852941176470588, "acc_norm_stderr": 0.03035969707904611 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.5359477124183006, "acc_stderr": 0.02017548876548405, "acc_norm": 0.5359477124183006, "acc_norm_stderr": 0.02017548876548405 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.5909090909090909, "acc_stderr": 0.04709306978661895, "acc_norm": 0.5909090909090909, "acc_norm_stderr": 0.04709306978661895 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.6530612244897959, "acc_stderr": 0.030472526026726492, "acc_norm": 0.6530612244897959, "acc_norm_stderr": 0.030472526026726492 }, "harness|hendrycksTest-sociology|5": { "acc": 0.7164179104477612, "acc_stderr": 0.03187187537919796, "acc_norm": 0.7164179104477612, "acc_norm_stderr": 0.03187187537919796 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-virology|5": { "acc": 0.4578313253012048, "acc_stderr": 0.0387862677100236, "acc_norm": 0.4578313253012048, "acc_norm_stderr": 0.0387862677100236 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.7251461988304093, "acc_stderr": 0.034240429246915824, "acc_norm": 0.7251461988304093, "acc_norm_stderr": 0.034240429246915824 }, "harness|truthfulqa:mc|0": { "mc1": 0.412484700122399, "mc1_stderr": 0.01723329939957122, "mc2": 0.5940288949043588, "mc2_stderr": 0.015208554054531144 } }