open-llm-leaderboard-old/details_uukuguy__speechless-code-mistral-7b-v1.0

该数据集是在评估模型uukuguy/speechless-code-mistral-7b-v1.0时自动创建的，用于Open LLM Leaderboard的评估。数据集包含64个配置，每个配置对应一个评估任务。数据集由3次运行生成，每次运行的结果作为特定分割存储在配置中，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

该数据集是在对模型 uukuguy/speechless-code-mistral-7b-v1.0 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 64 个配置，每个配置对应一个评估任务。
• 数据集从 3 次运行中创建，每次运行在每个配置中作为一个特定的分割存在，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。

数据加载示例

python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_uukuguy__speechless-code-mistral-7b-v1.0", "harness_winogrande_5", split="train")

最新结果

以下是 2023-12-08T00:30:08.150409 运行的最新结果：

python { "all": { "acc": 0.6328087510139756, "acc_stderr": 0.03241662679481022, "acc_norm": 0.6370452055948831, "acc_norm_stderr": 0.033063806342390464, "mc1": 0.33414932680538556, "mc1_stderr": 0.016512530677150538, "mc2": 0.4789652694280945, "mc2_stderr": 0.01485651327015513 }, "harness|arc:challenge|25": { "acc": 0.5708191126279863, "acc_stderr": 0.014464085894870655, "acc_norm": 0.6117747440273038, "acc_norm_stderr": 0.014241614207414044 }, "harness|hellaswag|10": { "acc": 0.6405098585939056, "acc_stderr": 0.004788703173474743, "acc_norm": 0.8376817367058355, "acc_norm_stderr": 0.003679889125399815 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.26, "acc_stderr": 0.04408440022768079, "acc_norm": 0.26, "acc_norm_stderr": 0.04408440022768079 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.562962962962963, "acc_stderr": 0.042849586397534015, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.042849586397534015 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6842105263157895, "acc_stderr": 0.03782728980865469, "acc_norm": 0.6842105263157895, "acc_norm_stderr": 0.03782728980865469 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880274, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880274 }, "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": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6184971098265896, "acc_stderr": 0.03703851193099521, "acc_norm": 0.6184971098265896, "acc_norm_stderr": 0.03703851193099521 }, "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": 0.76, "acc_stderr": 0.042923469599092816, "acc_norm": 0.76, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5659574468085107, "acc_stderr": 0.03240038086792747, "acc_norm": 0.5659574468085107, "acc_norm_stderr": 0.03240038086792747 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555497, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555497 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.02530590624159063, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.02530590624159063 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4523809523809524, "acc_stderr": 0.044518079590553275, "acc_norm": 0.4523809523809524, "acc_norm_stderr": 0.044518079590553275 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7580645161290323, "acc_stderr": 0.02436259969303108, "acc_norm": 0.7580645161290323, "acc_norm_stderr": 0.02436259969303108 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7575757575757576, "acc_stderr": 0.03346409881055953, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.03346409881055953 }, "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": 0.8963730569948186, "acc_stderr": 0.02199531196364424, "acc_norm": 0.8963730569948186, "acc_norm_stderr": 0.02199531196364424 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6538461538461539, "acc_stderr": 0.024121125416941183, "acc_norm": 0.6538461538461539, "acc_norm_stderr": 0.024121125416941183 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.31851851851851853, "acc_stderr": 0.02840653309060846, "acc_norm": 0.31851851851851853, "acc_norm_stderr": 0.02840653309060846 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.7142857142857143, "acc_stderr": 0.029344572500634335, "acc_norm": 0.7142857142857143, "acc_norm_stderr": 0.029344572500634335 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.31125827814569534, "acc_stderr": 0.03780445850526733, "acc_norm": 0.31125827814569534, "acc_norm_stderr": 0.03780445850526733 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8293577981651377, "acc_stderr": 0.016129271025099857, "acc_norm": 0.8293577981651377, "acc_norm_stderr": 0.016129271025099857 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5092592592592593, "acc_stderr": 0.034093869469927006, "acc_norm": 0.5092592592592593, "acc_norm_stderr": 0.034093869469927006 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.7745098039215687, "acc_stderr": 0.02933116229425174, "acc_norm": 0.7745098039215687, "acc_norm_stderr": 0.02933116229425174 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7679324894514767, "acc_stderr": 0.027479744550808514, "acc_norm": 0.7679324894514767, "acc_norm_stderr": 0.027479744550808514 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.695067264573991, "acc_stderr": 0.030898610882477518, "acc_norm": 0.695067264573991, "acc_norm_stderr": 0.030898610882477518 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7786259541984732, "acc_stderr": 0.03641297081313729, "acc_norm": 0.7786259541984732, "acc_norm_stderr": 0.03641297081313729 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8099173553719008, "acc_stderr": 0.03581796951709282, "acc_norm": 0.8099173553719008, "acc_norm_stderr": 0.03581796951709282 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7222222222222222, "acc_stderr": 0.04330043749650741, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.04330043749650741 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7361963190184049, "acc_stderr": 0.034624199316156234, "acc_norm": 0.7361963190184049, "acc_norm_stderr": 0.034624199316156234 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.5, "acc_stderr": 0.04745789978762494, "acc_norm": 0.5, "acc_norm_stderr": 0.04745789978762494 }, "harness|hendrycksTest-management|5": { "acc": 0.7572815533980582, "acc_stderr": 0.04245022486384495, "acc_norm": 0.7572815533980582, "acc_norm_stderr": 0.04245022486384495 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8547008547008547, "acc_stderr": 0.023086635086841407, "acc_norm": 0.8547008547008547, "acc_norm_stderr": 0.023086635086841407 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8173690932311622, "acc_stderr": 0.013816335389973147, "acc_norm": 0.8173690932311622, "acc_norm_stderr": 0.013816335389973147 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7225433526011561, "acc_stderr": 0.024105712607754307, "acc_norm": 0.7225433526011561, "acc_norm_stderr": 0.024105712607754307 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.34301675977653634, "acc_stderr": 0.015876912673057728, "acc_norm": 0.34301675977653634, "acc_norm_stderr": 0.015876912673057728 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.738562091503268, "acc_stderr": 0.025160998214292456, "acc_norm": 0.738562091503268, "acc_norm_stderr": 0.025160998214292456 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.7234726688102894, "acc_stderr": 0.02540383297817961, "acc_norm": 0.7234726688102894, "acc_norm_stderr": 0.02540383297817961 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.75, "acc_stderr": 0.02409347123262133, "acc_norm": 0.75, "acc_norm_stderr": 0.02409347123262133 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.4929078014184397, "acc_stderr": 0.02982449855912901, "acc_norm": 0.4929078014184397, "acc_norm_stderr": 0.02982449855912901 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4954367666232073, "acc_stderr": 0.012769704263117528, "acc_norm": 0.4954367666232073, "acc_norm_stderr": 0.012769704263117528 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6838235294117647, "acc_stderr": 0.028245687391462927, "acc_norm": 0.6838235294117647, "acc_norm_stderr": 0.028245687391462927 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.6748366013071896, "acc_stderr": 0.01895088677080631, "acc_norm": 0.6748366013071896, "acc_norm_stderr": 0.01895088677080631 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6636363636363637, "acc_stderr": 0.04525393596302506, "acc_norm": 0.6636363636363637, "acc_norm_stderr": 0.04525393596302506 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7224489795918367, "acc_stderr": 0.02866685779027465, "acc_norm": 0.7224489795918367, "acc_norm_stderr": 0.02866685779027465 }, "harness|hendrycksTest-sociology|5": { "acc": 0.8208955223880597, "acc_stderr": 0.027113286753111837, "acc_norm": 0.8208955223880597, "acc_norm_stderr": 0.027113286753111837 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.86, "acc_stderr": 0.034873508801977704, "acc_norm": 0.86, "acc_norm_stderr": 0.034873508801977704 }, "harness|hendrycksTest-virology|5": { "acc": 0.5481927710843374, "acc_stderr": 0.03874371556587953, "acc_norm": 0.5481927710843374, "acc_norm_stderr": 0.03874371556587953 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8187134502923976, "acc_stderr": 0.029547741687640038, "acc_norm": 0.8187134502923976, "acc_norm_stderr": 0.029547741687640038 }, "harness|truthfulqa:mc|0": { "mc1": 0.33414932680538556, "mc1_stderr": 0.016512530677150538, "mc2": 0.4789652694280945, "mc2_stderr": 0.01485651327015513 }, "harness|winogrande|5": { "acc": 0.7837411207576953, "acc_stderr": 0.011570614861409348 }, "harness|gsm8k|5": { "acc": 0.4700530705079606, "acc_stderr": 0.013747759685444703 } }