open-llm-leaderboard-old/details_migtissera__SynthIA-7B-v1.5
收藏数据集概述
数据集摘要
该数据集是在评估模型migtissera/SynthIA-7B-v1.5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：64个配置，每个配置对应一个评估任务。
- 创建来源：从1次运行中创建。每个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：一个名为"results"的额外配置存储了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_migtissera__SynthIA-7B-v1.5_public", "harness_winogrande_5", split="train")
最新结果
这些是最新的结果，来自2023-11-09T14:41:56.883085的运行： python { "all": { "acc": 0.6291968571108129, "acc_stderr": 0.03252538162461919, "acc_norm": 0.63804599014876, "acc_norm_stderr": 0.03323519542303871, "mc1": 0.35128518971848227, "mc1_stderr": 0.016711358163544403, "mc2": 0.5131996962275648, "mc2_stderr": 0.015337988977122931, "em": 0.1875, "em_stderr": 0.003997164044486006, "f1": 0.26010591442953035, "f1_stderr": 0.004042449995216609 }, "harness|arc:challenge|25": { "acc": 0.5870307167235495, "acc_stderr": 0.014388344935398324, "acc_norm": 0.6271331058020477, "acc_norm_stderr": 0.014131176760131172 }, "harness|hellaswag|10": { "acc": 0.6432981477793268, "acc_stderr": 0.0047804672709117705, "acc_norm": 0.833698466440948, "acc_norm_stderr": 0.0037159010850549967 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695236, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695236 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6148148148148148, "acc_stderr": 0.04203921040156279, "acc_norm": 0.6148148148148148, "acc_norm_stderr": 0.04203921040156279 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6644736842105263, "acc_stderr": 0.038424985593952694, "acc_norm": 0.6644736842105263, "acc_norm_stderr": 0.038424985593952694 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6981132075471698, "acc_stderr": 0.02825420034443866, "acc_norm": 0.6981132075471698, "acc_norm_stderr": 0.02825420034443866 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6944444444444444, "acc_stderr": 0.03852084696008534, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.03852084696008534 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.036430371689585475, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.036430371689585475 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.38235294117647056, "acc_stderr": 0.04835503696107223, "acc_norm": 0.38235294117647056, "acc_norm_stderr": 0.04835503696107223 }, "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": 0.5957446808510638, "acc_stderr": 0.03208115750788684, "acc_norm": 0.5957446808510638, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.43859649122807015, "acc_stderr": 0.04668000738510455, "acc_norm": 0.43859649122807015, "acc_norm_stderr": 0.04668000738510455 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5448275862068965, "acc_stderr": 0.04149886942192117, "acc_norm": 0.5448275862068965, "acc_norm_stderr": 0.04149886942192117 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3941798941798942, "acc_stderr": 0.02516798233389414, "acc_norm": 0.3941798941798942, "acc_norm_stderr": 0.02516798233389414 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768176, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768176 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7645161290322581, "acc_stderr": 0.02413763242933771, "acc_norm": 0.7645161290322581, "acc_norm_stderr": 0.02413763242933771 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4975369458128079, "acc_stderr": 0.03517945038691063, "acc_norm": 0.4975369458128079, "acc_norm_stderr": 0.03517945038691063 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "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": 0.7878787878787878, "acc_stderr": 0.029126522834586818, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.029126522834586818 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8652849740932642, "acc_stderr": 0.02463978909770944, "acc_norm": 0.8652849740932642, "acc_norm_stderr": 0.02463978909770944 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.023946724741563973, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.023946724741563973 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251976, "acc
