open-llm-leaderboard-old/details_distilgpt2
收藏数据集概述
数据集名称
Evaluation run of distilgpt2
数据集描述
该数据集是在对模型distilgpt2进行评估运行期间自动创建的，用于Open LLM Leaderboard。
数据集组成
数据集由63个配置组成，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。
额外配置
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_distilgpt2", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-16T13:25:51.422801运行的最新结果：
python { "all": { "acc": 0.24791527761428814, "acc_stderr": 0.030281954866030584, "acc_norm": 0.2481142819487892, "acc_norm_stderr": 0.03108662123022961, "mc1": 0.24969400244798043, "mc1_stderr": 0.015152286907148128, "mc2": 0.444910866699754, "mc2_stderr": 0.015279069341683332 }, "harness|arc:challenge|25": { "acc": 0.18088737201365188, "acc_stderr": 0.011248574467407024, "acc_norm": 0.2226962457337884, "acc_norm_stderr": 0.012158314774829931 }, "harness|hellaswag|10": { "acc": 0.2705636327424816, "acc_stderr": 0.0044334307903494095, "acc_norm": 0.2758414658434575, "acc_norm_stderr": 0.004460238879247437 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.04163331998932268, "acc_norm": 0.22, "acc_norm_stderr": 0.04163331998932268 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.24444444444444444, "acc_stderr": 0.03712537833614866, "acc_norm": 0.24444444444444444, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.17763157894736842, "acc_stderr": 0.031103182383123398, "acc_norm": 0.17763157894736842, "acc_norm_stderr": 0.031103182383123398 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.22264150943396227, "acc_stderr": 0.0256042334708991, "acc_norm": 0.22264150943396227, "acc_norm_stderr": 0.0256042334708991 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.2222222222222222, "acc_stderr": 0.03476590104304134, "acc_norm": 0.2222222222222222, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.17, "acc_stderr": 0.03775251680686371, "acc_norm": 0.17, "acc_norm_stderr": 0.03775251680686371 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.18, "acc_stderr": 0.03861229196653694, "acc_norm": 0.18, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.27, "acc_stderr": 0.04461960433384739, "acc_norm": 0.27, "acc_norm_stderr": 0.04461960433384739 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.20809248554913296, "acc_stderr": 0.030952890217749895, "acc_norm": 0.20809248554913296, "acc_norm_stderr": 0.030952890217749895 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.20588235294117646, "acc_stderr": 0.04023382273617747, "acc_norm": 0.20588235294117646, "acc_norm_stderr": 0.04023382273617747 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.21, "acc_stderr": 0.040936018074033256, "acc_norm": 0.21, "acc_norm_stderr": 0.040936018074033256 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.28085106382978725, "acc_stderr": 0.029379170464124818, "acc_norm": 0.28085106382978725, "acc_norm_stderr": 0.029379170464124818 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.2631578947368421, "acc_stderr": 0.04142439719489362, "acc_norm": 0.2631578947368421, "acc_norm_stderr": 0.04142439719489362 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.30344827586206896, "acc_stderr": 0.038312260488503336, "acc_norm": 0.30344827586206896, "acc_norm_stderr": 0.038312260488503336 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.2566137566137566, "acc_stderr": 0.022494510767503154, "acc_norm": 0.2566137566137566, "acc_norm_stderr": 0.022494510767503154 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.1984126984126984, "acc_stderr": 0.03567016675276865, "acc_norm": 0.1984126984126984, "acc_norm_stderr": 0.03567016675276865 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.15, "acc_stderr": 0.0358870281282637, "acc_norm": 0.15, "acc_norm_stderr": 0.0358870281282637 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.3193548387096774, "acc_stderr": 0.026522709674667768, "acc_norm": 0.3193548387096774, "acc_norm_stderr": 0.026522709674667768 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.30049261083743845, "acc_stderr": 0.03225799476233483, "acc_norm": 0.30049261083743845, "acc_norm_stderr": 0.03225799476233483 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.2, "acc_stderr": 0.04020151261036846, "acc_norm": 0.2, "acc_norm_stderr": 0.04020151261036846 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.21818181818181817, "acc_stderr": 0.03225078108306289, "acc_norm": 0.21818181818181817, "acc_norm_stderr": 0.03225078108306289 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.2878787878787879, "acc_stderr": 0.03225883512300992, "acc_norm": 0.2878787878787879, "acc_norm_stderr": 0.03225883512300992 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.23316062176165803, "acc_stderr": 0.030516111371476008, "acc_norm": 0.23316062176165803, "acc_norm_stderr": 0.030516111371476008 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.3128205128205128, "acc_stderr": 0.023507579020645347, "acc_norm": 0.3128205128205128, "acc_norm_stderr": 0.023507579020645347 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26296296296296295, "acc_stderr": 0.026842057873833706, "acc_norm": 0.26296296296296295, "acc_norm_stderr": 0.0268420
