open-llm-leaderboard/details_StarFox7__gemma-2b-dpo-v1

数据集`Evaluation run of StarFox7/gemma-2b-dpo-v1`是在模型`StarFox7/gemma-2b-dpo-v1`在`Open LLM Leaderboard`上的评估运行过程中自动生成的。该数据集包含63个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果存储为特定配置中的一个分割，分割名称使用运行的时间戳。`train`分割始终指向最新的结果。此外，`results`配置存储了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。

原始信息汇总

数据集概述

数据集简介

该数据集是在对模型 StarFox7/gemma-2b-dpo-v1 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。

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，每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
• "train" 分割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 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_StarFox7__gemma-2b-dpo-v1", "harness_winogrande_5", split="train")

最新结果

以下是 2024-03-27T18:31:10.536049 运行的最新结果：

python { "all": { "acc": 0.3820945619523406, "acc_stderr": 0.034010077446991686, "acc_norm": 0.38499722425720306, "acc_norm_stderr": 0.034787029275134565, "mc1": 0.21664626682986537, "mc1_stderr": 0.014421468452506985, "mc2": 0.3314959220011785, "mc2_stderr": 0.014118925834037833 }, "harness|arc:challenge|25": { "acc": 0.5042662116040956, "acc_stderr": 0.014610858923956959, "acc_norm": 0.5187713310580204, "acc_norm_stderr": 0.014601090150633964 }, "harness|hellaswag|10": { "acc": 0.5360485958972316, "acc_stderr": 0.004976796060456436, "acc_norm": 0.7087233618801035, "acc_norm_stderr": 0.0045342213500461186 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.3925925925925926, "acc_stderr": 0.04218506215368879, "acc_norm": 0.3925925925925926, "acc_norm_stderr": 0.04218506215368879 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.3223684210526316, "acc_stderr": 0.03803510248351585, "acc_norm": 0.3223684210526316, "acc_norm_stderr": 0.03803510248351585 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.37358490566037733, "acc_stderr": 0.029773082713319875, "acc_norm": 0.37358490566037733, "acc_norm_stderr": 0.029773082713319875 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.375, "acc_stderr": 0.04048439222695598, "acc_norm": 0.375, "acc_norm_stderr": 0.04048439222695598 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.24, "acc_stderr": 0.042923469599092816, "acc_norm": 0.24, "acc_norm_stderr": 0.042923469599092816 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.3236994219653179, "acc_stderr": 0.035676037996391706, "acc_norm": 0.3236994219653179, "acc_norm_stderr": 0.035676037996391706 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.17647058823529413, "acc_stderr": 0.037932811853078105, "acc_norm": 0.17647058823529413, "acc_norm_stderr": 0.037932811853078105 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.34893617021276596, "acc_stderr": 0.031158522131357787, "acc_norm": 0.34893617021276596, "acc_norm_stderr": 0.031158522131357787 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3157894736842105, "acc_stderr": 0.04372748290278007, "acc_norm": 0.3157894736842105, "acc_norm_stderr": 0.04372748290278007 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4068965517241379, "acc_stderr": 0.04093793981266237, "acc_norm": 0.4068965517241379, "acc_norm_stderr": 0.04093793981266237 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2751322751322751, "acc_stderr": 0.02300008685906863, "acc_norm": 0.2751322751322751, "acc_norm_stderr": 0.02300008685906863 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.30952380952380953, "acc_stderr": 0.04134913018303316, "acc_norm": 0.30952380952380953, "acc_norm_stderr": 0.04134913018303316 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.25, "acc_stderr": 0.04351941398892446, "acc_norm": 0.25, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.4064516129032258, "acc_stderr": 0.02794172734625631, "acc_norm": 0.4064516129032258, "acc_norm_stderr": 0.02794172734625631 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.33497536945812806, "acc_stderr": 0.033208527423483104, "acc_norm": 0.33497536945812806, "acc_norm_stderr": 0.033208527423483104 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.4909090909090909, "acc_stderr": 0.03903698647748441, "acc_norm": 0.4909090909090909, "acc_norm_stderr": 0.03903698647748441 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.3888888888888889, "acc_stderr": 0.0347327959083696, "acc_norm": 0.3888888888888889, "acc_norm_stderr": 0.0347327959083696 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.42487046632124353, "acc_stderr": 0.0356747133521254, "acc_norm": 0.42487046632124353, "acc_norm_stderr": 0.0356747133521254 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3435897435897436, "acc_stderr": 0.024078696580635484, "acc_norm": 0.3435897435897436, "acc_norm_stderr": 0.024078696580635484 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.23703703703703705, "acc_stderr": 0.02592887613276612, "acc_norm": 0.23703703703703705, "acc_norm_stderr":