open-llm-leaderboard-old/details_splm__openchat-spin-slimorca-iter0
收藏数据集概述
该数据集是在模型 splm/openchat-spin-slimorca-iter0 的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_splm__openchat-spin-slimorca-iter0", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-22T12:34:05.402609 运行的最新结果：
python { "all": { "acc": 0.6469374738054939, "acc_stderr": 0.032070938422677234, "acc_norm": 0.6481950421550251, "acc_norm_stderr": 0.03272367325547948, "mc1": 0.40514075887392903, "mc1_stderr": 0.01718561172775337, "mc2": 0.5687270445915593, "mc2_stderr": 0.015417548365825899 }, "harness|arc:challenge|25": { "acc": 0.6356655290102389, "acc_stderr": 0.014063260279882419, "acc_norm": 0.6715017064846417, "acc_norm_stderr": 0.013724978465537307 }, "harness|hellaswag|10": { "acc": 0.6432981477793268, "acc_stderr": 0.004780467270911773, "acc_norm": 0.8360884285998805, "acc_norm_stderr": 0.0036943873611776546 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720386, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720386 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6907894736842105, "acc_stderr": 0.037610708698674805, "acc_norm": 0.6907894736842105, "acc_norm_stderr": 0.037610708698674805 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.64, "acc_stderr": 0.04824181513244218, "acc_norm": 0.64, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7094339622641509, "acc_stderr": 0.02794321998933714, "acc_norm": 0.7094339622641509, "acc_norm_stderr": 0.02794321998933714 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7708333333333334, "acc_stderr": 0.03514697467862388, "acc_norm": 0.7708333333333334, "acc_norm_stderr": 0.03514697467862388 }, "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": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.04852365870939099, "acc_norm": 0.37, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247078, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247078 }, "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": 0.73, "acc_stderr": 0.0446196043338474, "acc_norm": 0.73, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5914893617021276, "acc_stderr": 0.032134180267015755, "acc_norm": 0.5914893617021276, "acc_norm_stderr": 0.032134180267015755 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5087719298245614, "acc_stderr": 0.04702880432049615, "acc_norm": 0.5087719298245614, "acc_norm_stderr": 0.04702880432049615 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5655172413793104, "acc_stderr": 0.04130740879555498, "acc_norm": 0.5655172413793104, "acc_norm_stderr": 0.04130740879555498 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42592592592592593, "acc_stderr": 0.02546714904546955, "acc_norm": 0.42592592592592593, "acc_norm_stderr": 0.02546714904546955 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.48412698412698413, "acc_stderr": 0.04469881854072606, "acc_norm": 0.48412698412698413, "acc_norm_stderr": 0.04469881854072606 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.28, "acc_stderr": 0.04512608598542127, "acc_norm": 0.28, "acc_norm_stderr": 0.04512608598542127 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7677419354838709, "acc_stderr": 0.024022256130308235, "acc_norm": 0.7677419354838709, "acc_norm_stderr": 0.024022256130308235 }, "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": 0.72, "acc_stderr": 0.04512608598542129, "acc_norm": 0.72, "acc_norm_stderr": 0.04512608598542129 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7757575757575758, "acc_stderr": 0.03256866661681102, "acc_norm": 0.7757575757575758, "acc_norm_stderr": 0.03256866661681102 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7575757575757576, "acc_stderr": 0.030532892233932026, "acc_norm": 0.7575757575757576, "acc_norm_stderr": 0.030532892233932026 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033467, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033467 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6487179487179487, "acc_stderr": 0.024203665177902803, "acc_norm": 0.6487179487179487, "acc_norm_stderr": 0.024203665177902803 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.36666666666666664, "acc_stderr": 0.02938162072646507, "acc_norm": 0.36666666666666664, "acc_norm_stderr
