open-llm-leaderboard-old/details_G-reen__EXPERIMENT-DPO-m7b2-2-merged
收藏数据集概述
数据集简介
该数据集是在评估模型 G-reen/EXPERIMENT-DPO-m7b2-2-merged 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集结构
- 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割找到，分割名称使用运行的时间戳。
- 最新结果："train" 分割始终指向最新的结果。
- 结果汇总：一个额外的配置 "results" 存储所有运行的汇总结果，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_G-reen__EXPERIMENT-DPO-m7b2-2-merged", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-27T18:39:08.935024 运行 的最新结果：
python { "all": { "acc": 0.6201965389046622, "acc_stderr": 0.032792348538430306, "acc_norm": 0.6260182582000938, "acc_norm_stderr": 0.03346440993851948, "mc1": 0.2692778457772338, "mc1_stderr": 0.015528566637087288, "mc2": 0.4011302866179054, "mc2_stderr": 0.014061476060014856 }, "harness|arc:challenge|25": { "acc": 0.5622866894197952, "acc_stderr": 0.014497573881108285, "acc_norm": 0.5947098976109215, "acc_norm_stderr": 0.014346869060229321 }, "harness|hellaswag|10": { "acc": 0.6200955984863573, "acc_stderr": 0.004843708550386531, "acc_norm": 0.8247361083449513, "acc_norm_stderr": 0.0037941565512722795 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.28, "acc_stderr": 0.04512608598542128, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542128 }, "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": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.54, "acc_stderr": 0.05009082659620333, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620333 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6792452830188679, "acc_stderr": 0.028727502957880263, "acc_norm": 0.6792452830188679, "acc_norm_stderr": 0.028727502957880263 }, "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": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "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": 0.37254901960784315, "acc_stderr": 0.04810840148082636, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5361702127659574, "acc_stderr": 0.032600385118357715, "acc_norm": 0.5361702127659574, "acc_norm_stderr": 0.032600385118357715 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "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": 0.3968253968253968, "acc_stderr": 0.02519710107424649, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.02519710107424649 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.38095238095238093, "acc_stderr": 0.04343525428949098, "acc_norm": 0.38095238095238093, "acc_norm_stderr": 0.04343525428949098 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7322580645161291, "acc_stderr": 0.025189006660212385, "acc_norm": 0.7322580645161291, "acc_norm_stderr": 0.025189006660212385 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5221674876847291, "acc_stderr": 0.03514528562175008, "acc_norm": 0.5221674876847291, "acc_norm_stderr": 0.03514528562175008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145633, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145633 }, "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": 0.7474747474747475, "acc_stderr": 0.030954055470365897, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.030954055470365897 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.844559585492228, "acc_stderr": 0.02614848346915331, "acc_norm": 0.844559585492228, "acc_norm_stderr": 0.02614848346915331 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5974358974358974, "acc_stderr": 0.024864995159767755, "acc_norm": 0.5974358974358974, "acc_norm_stderr": 0.024864995159767755 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3333333333333333, "acc_stderr": 0.028742040903948485, "acc_norm": 0.33333333
