open-llm-leaderboard-old/details_mervinpraison__tamil-large-language-model-7b-v1.0
收藏数据集概述
数据集简介
该数据集是在评估模型mervinpraison/tamil-large-language-model-7b-v1.0在Open LLM Leaderboard上的运行过程中自动创建的。
数据集组成
- 配置数量：63个配置，每个配置对应一个评估任务。
- 数据来源：数据集由1次运行创建，每个运行在每个配置中作为一个特定的分片存在，分片名称使用运行的时间戳。
- 最新结果："train"分片总是指向最新的结果。
- 聚合结果：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_mervinpraison__tamil-large-language-model-7b-v1.0", "harness_winogrande_5", split="train")
最新结果
以下是最新结果的摘要： python { "all": { "acc": 0.6370328514723723, "acc_stderr": 0.03208106599521034, "acc_norm": 0.6414401680177975, "acc_norm_stderr": 0.03271531558128225, "mc1": 0.31211750305997554, "mc1_stderr": 0.01622075676952093, "mc2": 0.4508914096363667, "mc2_stderr": 0.014596703529350155 }, "harness|arc:challenge|25": { "acc": 0.5580204778156996, "acc_stderr": 0.014512682523128345, "acc_norm": 0.6015358361774744, "acc_norm_stderr": 0.014306946052735563 }, "harness|hellaswag|10": { "acc": 0.6179047998406691, "acc_stderr": 0.0048490659626921305, "acc_norm": 0.8221469826727743, "acc_norm_stderr": 0.0038160747120605347 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.24, "acc_stderr": 0.04292346959909282, "acc_norm": 0.24, "acc_norm_stderr": 0.04292346959909282 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5259259259259259, "acc_stderr": 0.04313531696750575, "acc_norm": 0.5259259259259259, "acc_norm_stderr": 0.04313531696750575 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7039473684210527, "acc_stderr": 0.037150621549989056, "acc_norm": 0.7039473684210527, "acc_norm_stderr": 0.037150621549989056 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6490566037735849, "acc_stderr": 0.029373646253234686, "acc_norm": 0.6490566037735849, "acc_norm_stderr": 0.029373646253234686 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7569444444444444, "acc_stderr": 0.03586879280080341, "acc_norm": 0.7569444444444444, "acc_norm_stderr": 0.03586879280080341 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.653179190751445, "acc_stderr": 0.036291466701596636, "acc_norm": 0.653179190751445, "acc_norm_stderr": 0.036291466701596636 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.048580835742663454, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.048580835742663454 }, "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": 0.6085106382978723, "acc_stderr": 0.03190701242326812, "acc_norm": 0.6085106382978723, "acc_norm_stderr": 0.03190701242326812 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.45614035087719296, "acc_stderr": 0.046854730419077895, "acc_norm": 0.45614035087719296, "acc_norm_stderr": 0.046854730419077895 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.593103448275862, "acc_stderr": 0.04093793981266237, "acc_norm": 0.593103448275862, "acc_norm_stderr": 0.04093793981266237 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.48148148148148145, "acc_stderr": 0.025733641991838987, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.025733641991838987 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7967741935483871, "acc_stderr": 0.02289168798455494, "acc_norm": 0.7967741935483871, "acc_norm_stderr": 0.02289168798455494 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5369458128078818, "acc_stderr": 0.035083705204426656, "acc_norm": 0.5369458128078818, "acc_norm_stderr": 0.035083705204426656 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7333333333333333, "acc_stderr": 0.03453131801885415, "acc_norm": 0.7333333333333333, "acc_norm_stderr": 0.03453131801885415 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8181818181818182, "acc_stderr": 0.027479603010538797, "acc_norm": 0.8181818181818182, "acc_norm_stderr": 0.027479603010538797 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8911917098445595, "acc_stderr": 0.02247325333276878, "acc_norm": 0.8911917098445595, "acc_norm_stderr": 0.02247325333276878 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6256410256410256, "acc_stderr": 0.024537591572830506, "acc_norm": 0.6256410256410256, "acc_norm_stderr": 0.024537591572830506 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.029670906124630893, "acc_norm": 0.
