open-llm-leaderboard-old/details_SCE__Mistral-7B-math-ia3-pruned20
收藏数据集概述
数据集简介
该数据集是在评估模型 SCE/Mistral-7B-math-ia3-pruned20 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。
- 额外的 "results" 配置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_SCE__Mistral-7B-math-ia3-pruned20", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-29T08:07:52.412937 运行的最新结果：
python { "all": { "acc": 0.6055660350620623, "acc_stderr": 0.033190282510517935, "acc_norm": 0.6099875699478283, "acc_norm_stderr": 0.03385986318812193, "mc1": 0.5201958384332925, "mc1_stderr": 0.017489216849737053, "mc2": 0.6773630200722127, "mc2_stderr": 0.015189227668395784 }, "harness|arc:challenge|25": { "acc": 0.5819112627986348, "acc_stderr": 0.01441398839699608, "acc_norm": 0.6305460750853242, "acc_norm_stderr": 0.014104578366491888 }, "harness|hellaswag|10": { "acc": 0.6550487950607449, "acc_stderr": 0.004743808792037865, "acc_norm": 0.8441545508862777, "acc_norm_stderr": 0.003619674864035016 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.29, "acc_stderr": 0.045604802157206845, "acc_norm": 0.29, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6381578947368421, "acc_stderr": 0.03910525752849723, "acc_norm": 0.6381578947368421, "acc_norm_stderr": 0.03910525752849723 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.58, "acc_stderr": 0.049604496374885836, "acc_norm": 0.58, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.02906722014664483, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.02906722014664483 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6805555555555556, "acc_stderr": 0.038990736873573344, "acc_norm": 0.6805555555555556, "acc_norm_stderr": 0.038990736873573344 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.049888765156985884, "acc_norm": 0.44, "acc_norm_stderr": 0.049888765156985884 }, "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": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5838150289017341, "acc_stderr": 0.03758517775404947, "acc_norm": 0.5838150289017341, "acc_norm_stderr": 0.03758517775404947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726367, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726367 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5404255319148936, "acc_stderr": 0.03257901482099834, "acc_norm": 0.5404255319148936, "acc_norm_stderr": 0.03257901482099834 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.38596491228070173, "acc_stderr": 0.04579639422070434, "acc_norm": 0.38596491228070173, "acc_norm_stderr": 0.04579639422070434 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5862068965517241, "acc_stderr": 0.04104269211806232, "acc_norm": 0.5862068965517241, "acc_norm_stderr": 0.04104269211806232 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.373015873015873, "acc_stderr": 0.02490699045899257, "acc_norm": 0.373015873015873, "acc_norm_stderr": 0.02490699045899257 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.40476190476190477, "acc_stderr": 0.04390259265377563, "acc_norm": 0.40476190476190477, "acc_norm_stderr": 0.04390259265377563 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6645161290322581, "acc_stderr": 0.02686020644472435, "acc_norm": 0.6645161290322581, "acc_norm_stderr": 0.02686020644472435 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.03517603540361008, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.03517603540361008 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.703030303030303, "acc_stderr": 0.0356796977226805, "acc_norm": 0.703030303030303, "acc_norm_stderr": 0.0356796977226805 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7575757575757576, "acc_stderr": 0.030532892233932022, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.030532892233932022 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.02649905770139744, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.02649905770139744 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5461538461538461, "acc_stderr": 0.025242770987126184, "acc_norm": 0.5461538461538461, "acc_norm_stderr": 0.025242770987126184 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3, "acc_stderr": 0.027940457136228402, "acc_norm": 0.3, "acc_norm_stderr": 0.027940
