open-llm-leaderboard-old/details_vanillaOVO__merge_7B_state_2
收藏数据集概述
数据集 Evaluation run of vanillaOVO/merge_7B_state_2 是在模型 vanillaOVO/merge_7B_state_2 在 Open LLM Leaderboard 上的评估运行期间自动创建的。
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。
- 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_vanillaOVO__merge_7B_state_2", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-24T15:10:53.601018 运行的最新结果：
python { "all": { "acc": 0.6561162394606307, "acc_stderr": 0.03201712529877245, "acc_norm": 0.6554270448426979, "acc_norm_stderr": 0.03268637846171269, "mc1": 0.5630354957160343, "mc1_stderr": 0.01736384450319596, "mc2": 0.7136957056689134, "mc2_stderr": 0.014784423460406175 }, "harness|arc:challenge|25": { "acc": 0.7039249146757679, "acc_stderr": 0.01334091608524626, "acc_norm": 0.7312286689419796, "acc_norm_stderr": 0.012955065963710696 }, "harness|hellaswag|10": { "acc": 0.7126070503883688, "acc_stderr": 0.004516215206715354, "acc_norm": 0.8861780521808404, "acc_norm_stderr": 0.0031694581233577238 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6592592592592592, "acc_stderr": 0.04094376269996792, "acc_norm": 0.6592592592592592, "acc_norm_stderr": 0.04094376269996792 }, "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": 0.7169811320754716, "acc_stderr": 0.027724236492700914, "acc_norm": 0.7169811320754716, "acc_norm_stderr": 0.027724236492700914 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7777777777777778, "acc_stderr": 0.03476590104304134, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.03476590104304134 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6589595375722543, "acc_stderr": 0.036146654241808254, "acc_norm": 0.6589595375722543, "acc_norm_stderr": 0.036146654241808254 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4019607843137255, "acc_stderr": 0.048786087144669955, "acc_norm": 0.4019607843137255, "acc_norm_stderr": 0.048786087144669955 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "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": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878152, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878152 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42857142857142855, "acc_stderr": 0.02548718714785938, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.02548718714785938 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.46825396825396826, "acc_stderr": 0.04463112720677172, "acc_norm": 0.46825396825396826, "acc_norm_stderr": 0.04463112720677172 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.023415293433568525, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.023415293433568525 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.49261083743842365, "acc_stderr": 0.035176035403610084, "acc_norm": 0.49261083743842365, "acc_norm_stderr": 0.035176035403610084 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7878787878787878, "acc_stderr": 0.03192271569548301, "acc_norm": 0.7878787878787878, "acc_norm_stderr": 0.03192271569548301 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.797979797979798, "acc_stderr": 0.02860620428922987, "acc_norm": 0.797979797979798, "acc_norm_stderr": 0.02860620428922987 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.02098685459328973, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.02098685459328973 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6794871794871795, "acc_stderr": 0.02366129639396428, "acc_norm": 0.6794871794871795, "acc_norm_stderr": 0.02366129639396428 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.35185185185185186, "acc_stderr": 0.029116617606083008, "acc_norm": 0.35185185185185186, "acc_norm_stderr": 0.0291166176060
