open-llm-leaderboard-old/details_VAGOsolutions__Llama-3-SauerkrautLM-8b-Instruct
收藏数据集概述
数据集摘要
该数据集是在模型VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct在Open LLM Leaderboard上的评估运行期间自动创建的。
数据集组成
- 该数据集包含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，每个运行可以在每个配置中作为一个特定的分片找到，分片名称使用运行的时间戳。
- "train"分片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_VAGOsolutions__Llama-3-SauerkrautLM-8b-Instruct", "harness_winogrande_5", split="train")
最新结果
这些是最新结果，来自2024-04-23T07:01:47.328957的运行： python { "all": { "acc": 0.6838292280011203, "acc_stderr": 0.03142345546414635, "acc_norm": 0.6852457885676501, "acc_norm_stderr": 0.032049882648965654, "mc1": 0.5140758873929009, "mc1_stderr": 0.017496563717042786, "mc2": 0.6624826458272768, "mc2_stderr": 0.01534765802085052 }, "harness|arc:challenge|25": { "acc": 0.7226962457337884, "acc_stderr": 0.013082095839059376, "acc_norm": 0.7372013651877133, "acc_norm_stderr": 0.012862523175351335 }, "harness|hellaswag|10": { "acc": 0.7426807408882693, "acc_stderr": 0.004362633637374479, "acc_norm": 0.8941445927106154, "acc_norm_stderr": 0.003070237115326101 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.04171654161354543, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.04171654161354543 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7171052631578947, "acc_stderr": 0.03665349695640767, "acc_norm": 0.7171052631578947, "acc_norm_stderr": 0.03665349695640767 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.72, "acc_stderr": 0.04512608598542129, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7433962264150943, "acc_stderr": 0.02688064788905199, "acc_norm": 0.7433962264150943, "acc_norm_stderr": 0.02688064788905199 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8263888888888888, "acc_stderr": 0.031674733837957186, "acc_norm": 0.8263888888888888, "acc_norm_stderr": 0.031674733837957186 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6763005780346821, "acc_stderr": 0.0356760379963917, "acc_norm": 0.6763005780346821, "acc_norm_stderr": 0.0356760379963917 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.49019607843137253, "acc_stderr": 0.04974229460422817, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.79, "acc_stderr": 0.040936018074033256, "acc_norm": 0.79, "acc_norm_stderr": 0.040936018074033256 }, "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": 0.6052631578947368, "acc_stderr": 0.04598188057816542, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.04598188057816542 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6551724137931034, "acc_stderr": 0.03960933549451207, "acc_norm": 0.6551724137931034, "acc_norm_stderr": 0.03960933549451207 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.46296296296296297, "acc_stderr": 0.025680564640056882, "acc_norm": 0.46296296296296297, "acc_norm_stderr": 0.025680564640056882 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5158730158730159, "acc_stderr": 0.044698818540726076, "acc_norm": 0.5158730158730159, "acc_norm_stderr": 0.044698818540726076 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7806451612903226, "acc_stderr": 0.023540799358723274, "acc_norm": 0.7806451612903226, "acc_norm_stderr": 0.023540799358723274 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5812807881773399, "acc_stderr": 0.03471192860518468, "acc_norm": 0.5812807881773399, "acc_norm_stderr": 0.03471192860518468 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.03374402644139404, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.03374402644139404 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8585858585858586, "acc_stderr": 0.024825909793343346, "acc_norm": 0.8585858585858586, "acc_norm_stderr": 0.024825909793343346 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9119170984455959, "acc_stderr": 0.02045374660160103, "acc_norm": 0.9119170984455959, "acc_norm_stderr": 0.02045374660160103 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6564102564102564, "acc_stderr": 0.024078696580635467, "acc_norm": 0.6564102564102564, "acc_norm_stderr": 0.024078696580635467 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.02995824925008212, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.02995824925008212 }, "harness|hendrycksTest-high_school_microeconomics|5
