open-llm-leaderboard-old/details_jikaixuan__test_model
收藏数据集概述
该数据集是在评估模型 jikaixuan/test_model 在 Open LLM Leaderboard 上的运行过程中自动创建的。
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。
- 数据集由 1 次运行创建，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。
- 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_jikaixuan__test_model", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-30T01:50:31.139898 运行的最新结果：
python { "all": { "acc": 0.6083156130977855, "acc_stderr": 0.03325697047846345, "acc_norm": 0.6149057049790325, "acc_norm_stderr": 0.03395674600613233, "mc1": 0.40758873929008566, "mc1_stderr": 0.01720194923455311, "mc2": 0.575115982039762, "mc2_stderr": 0.015744867615337492 }, "harness|arc:challenge|25": { "acc": 0.5930034129692833, "acc_stderr": 0.01435639941800912, "acc_norm": 0.6228668941979523, "acc_norm_stderr": 0.014163366896192594 }, "harness|hellaswag|10": { "acc": 0.6490738896634136, "acc_stderr": 0.004762844770909858, "acc_norm": 0.8441545508862777, "acc_norm_stderr": 0.003619674864035017 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6, "acc_stderr": 0.04232073695151589, "acc_norm": 0.6, "acc_norm_stderr": 0.04232073695151589 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6052631578947368, "acc_stderr": 0.039777499346220734, "acc_norm": 0.6052631578947368, "acc_norm_stderr": 0.039777499346220734 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.56, "acc_stderr": 0.04988876515698589, "acc_norm": 0.56, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6490566037735849, "acc_stderr": 0.02937364625323469, "acc_norm": 0.6490566037735849, "acc_norm_stderr": 0.02937364625323469 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7013888888888888, "acc_stderr": 0.03827052357950756, "acc_norm": 0.7013888888888888, "acc_norm_stderr": 0.03827052357950756 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "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": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.630057803468208, "acc_stderr": 0.0368122963339432, "acc_norm": 0.630057803468208, "acc_norm_stderr": 0.0368122963339432 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.048971049527263666, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.048971049527263666 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.72, "acc_stderr": 0.04512608598542128, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542128 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5191489361702127, "acc_stderr": 0.032662042990646775, "acc_norm": 0.5191489361702127, "acc_norm_stderr": 0.032662042990646775 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4473684210526316, "acc_stderr": 0.04677473004491199, "acc_norm": 0.4473684210526316, "acc_norm_stderr": 0.04677473004491199 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5379310344827586, "acc_stderr": 0.04154659671707548, "acc_norm": 0.5379310344827586, "acc_norm_stderr": 0.04154659671707548 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.37566137566137564, "acc_stderr": 0.024942368931159795, "acc_norm": 0.37566137566137564, "acc_norm_stderr": 0.024942368931159795 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4444444444444444, "acc_stderr": 0.044444444444444495, "acc_norm": 0.4444444444444444, "acc_norm_stderr": 0.044444444444444495 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.4, "acc_stderr": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7483870967741936, "acc_stderr": 0.024685979286239963, "acc_norm": 0.7483870967741936, "acc_norm_stderr": 0.024685979286239963 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.67, "acc_stderr": 0.04725815626252609, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252609 }, "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": 0.7373737373737373, "acc_stderr": 0.03135305009533086, "acc_norm": 0.7373737373737373, "acc_norm_stderr": 0.03135305009533086 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8238341968911918, "acc_stderr": 0.02749350424454805, "acc_norm": 0.8238341968911918, "acc_norm_stderr": 0.02749350424454805 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6205128205128205, "acc_stderr": 0.02460362692409742, "acc_norm": 0.6205128205128205, "acc_norm_stderr": 0.02460362692409742 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.337037037037037, "acc_stderr": 0.028820884666253255, "acc_norm": 0.337037037037037, "acc_norm_stderr": 0.028820884666253255 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.684873949
