open-llm-leaderboard/details_openaccess-ai-collective__mistral-7b-slimorcaboros
收藏数据集概述
该数据集是在评估模型openaccess-ai-collective/mistral-7b-slimorcaboros在Open LLM Leaderboard上的运行过程中自动创建的。
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1次运行中创建，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。
- 额外的配置"results"存储所有运行的聚合结果，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_openaccess-ai-collective__mistral-7b-slimorcaboros_public", "harness_winogrande_5", split="train")
最新结果
以下是2023-11-14T19:06:13.668768运行的最新结果：
python { "all": { "acc": 0.6301042082006363, "acc_stderr": 0.032164201740811346, "acc_norm": 0.6380190670382948, "acc_norm_stderr": 0.03283508976201021, "mc1": 0.390452876376989, "mc1_stderr": 0.01707823074343145, "mc2": 0.5581158489169444, "mc2_stderr": 0.01565820515437776, "em": 0.03859060402684564, "em_stderr": 0.001972579977587539, "f1": 0.11617135067114018, "f1_stderr": 0.0024204909854951134 }, "harness|arc:challenge|25": { "acc": 0.6117747440273038, "acc_stderr": 0.014241614207414054, "acc_norm": 0.636518771331058, "acc_norm_stderr": 0.014056207319068285 }, "harness|hellaswag|10": { "acc": 0.650368452499502, "acc_stderr": 0.004758790172436686, "acc_norm": 0.8369846644094802, "acc_norm_stderr": 0.0036862475593618512 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.03894734487013316, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.03894734487013316 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.660377358490566, "acc_stderr": 0.029146904747798328, "acc_norm": 0.660377358490566, "acc_norm_stderr": 0.029146904747798328 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "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": 0.77, "acc_stderr": 0.04229525846816506, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816506 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5702127659574469, "acc_stderr": 0.03236214467715564, "acc_norm": 0.5702127659574469, "acc_norm_stderr": 0.03236214467715564 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.47368421052631576, "acc_stderr": 0.04697085136647863, "acc_norm": 0.47368421052631576, "acc_norm_stderr": 0.04697085136647863 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42063492063492064, "acc_stderr": 0.025424835086924, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.025424835086924 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7806451612903226, "acc_stderr": 0.023540799358723292, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723292 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4729064039408867, "acc_stderr": 0.03512819077876106, "acc_norm": 0.4729064039408867, "acc_norm_stderr": 0.03512819077876106 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252609, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252609 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.793939393939394, "acc_stderr": 0.0315841532404771, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.0315841532404771 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.803030303030303, "acc_stderr": 0.028335609732463362, "acc_norm": 0.803030303030303, "acc_norm_stderr": 0.028335609732463362 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.02338193534812143, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.02338193534812143 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6435897435897436, "acc_stderr": 0.02428314052946731, "acc_norm": 0.6435897435897436, "acc_norm_stderr": 0.02428314052946731 }, "harness|
