open-llm-leaderboard-old/details_SherlockAssistant__Mistral-7B-Instruct-Ukrainian
收藏数据集概述
数据集摘要
该数据集是在对模型 SherlockAssistant/Mistral-7B-Instruct-Ukrainian 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 "results" 配置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_SherlockAssistant__Mistral-7B-Instruct-Ukrainian", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-05T21:16:16.427255 运行的最新结果：
python { "all": { "acc": 0.631230613633757, "acc_stderr": 0.03266750104306204, "acc_norm": 0.6333894948380886, "acc_norm_stderr": 0.03333074370939577, "mc1": 0.4749082007343941, "mc1_stderr": 0.017481446804104003, "mc2": 0.6495262134981606, "mc2_stderr": 0.015081370696912105 }, "harness|arc:challenge|25": { "acc": 0.621160409556314, "acc_stderr": 0.014175915490000324, "acc_norm": 0.674061433447099, "acc_norm_stderr": 0.013697432466693252 }, "harness|hellaswag|10": { "acc": 0.6643098984266083, "acc_stderr": 0.004712660409846843, "acc_norm": 0.8580959968133838, "acc_norm_stderr": 0.0034823849566327793 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.04605661864718381, "acc_norm": 0.3, "acc_norm_stderr": 0.04605661864718381 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.04276349494376599, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.04276349494376599 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.03715062154998904, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.03715062154998904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.62, "acc_stderr": 0.048783173121456316, "acc_norm": 0.62, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.690566037735849, "acc_stderr": 0.028450154794118637, "acc_norm": 0.690566037735849, "acc_norm_stderr": 0.028450154794118637 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7083333333333334, "acc_stderr": 0.038009680605548594, "acc_norm": 0.7083333333333334, "acc_norm_stderr": 0.038009680605548594 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "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": 0.6069364161849711, "acc_stderr": 0.0372424959581773, "acc_norm": 0.6069364161849711, "acc_norm_stderr": 0.0372424959581773 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.73, "acc_stderr": 0.0446196043338474, "acc_norm": 0.73, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.49122807017543857, "acc_stderr": 0.04702880432049615, "acc_norm": 0.49122807017543857, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5793103448275863, "acc_stderr": 0.0411391498118926, "acc_norm": 0.5793103448275863, "acc_norm_stderr": 0.0411391498118926 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.40476190476190477, "acc_stderr": 0.025279850397404904, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.025279850397404904 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.49206349206349204, "acc_stderr": 0.044715725362943486, "acc_norm": 0.49206349206349204, "acc_norm_stderr": 0.044715725362943486 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6129032258064516, "acc_stderr": 0.02770935967503249, "acc_norm": 0.6129032258064516, "acc_norm_stderr": 0.02770935967503249 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.65, "acc_stderr": 0.047937248544110196, "acc_norm": 0.65, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.793939393939394, "acc_stderr": 0.03158415324047711, "acc_norm": 0.793939393939394, "acc_norm_stderr": 0.03158415324047711 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.02985751567338642, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.02985751567338642 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397443, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6307692307692307, "acc_stderr": 0.02446861524147892, "acc_norm": 0.6307692307692307, "acc_norm_stderr": 0.02446861524147892 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.02911661760608301, "acc_norm": 0.35185185185185186,
