open-llm-leaderboard-old/details_OpenBuddy__openbuddy-mistral2-7b-v20.2-32k
收藏数据集概述
数据集名称
Evaluation run of OpenBuddy/openbuddy-mistral2-7b-v20.2-32k
数据集描述
该数据集是在模型 OpenBuddy/openbuddy-mistral2-7b-v20.2-32k 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_OpenBuddy__openbuddy-mistral2-7b-v20.2-32k", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-27T20:15:52.994973 运行的最新结果：
python { "all": { "acc": 0.6064528394667296, "acc_stderr": 0.033156291025923365, "acc_norm": 0.6097883662192362, "acc_norm_stderr": 0.033824431680111434, "mc1": 0.36964504283965727, "mc1_stderr": 0.016898180706973895, "mc2": 0.5318060995560363, "mc2_stderr": 0.015423639616992663 }, "harness|arc:challenge|25": { "acc": 0.5307167235494881, "acc_stderr": 0.014583792546304037, "acc_norm": 0.5691126279863481, "acc_norm_stderr": 0.01447113339264247 }, "harness|hellaswag|10": { "acc": 0.6040629356701852, "acc_stderr": 0.004880515431323159, "acc_norm": 0.7944632543318064, "acc_norm_stderr": 0.00403267443344754 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.38, "acc_stderr": 0.048783173121456316, "acc_norm": 0.38, "acc_norm_stderr": 0.048783173121456316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5703703703703704, "acc_stderr": 0.042763494943765995, "acc_norm": 0.5703703703703704, "acc_norm_stderr": 0.042763494943765995 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.618421052631579, "acc_stderr": 0.03953173377749194, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.03953173377749194 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.57, "acc_stderr": 0.049756985195624284, "acc_norm": 0.57, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6641509433962264, "acc_stderr": 0.029067220146644826, "acc_norm": 0.6641509433962264, "acc_norm_stderr": 0.029067220146644826 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6388888888888888, "acc_stderr": 0.04016660030451233, "acc_norm": 0.6388888888888888, "acc_norm_stderr": 0.04016660030451233 }, "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": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.047258156262526045, "acc_norm": 0.33, "acc_norm_stderr": 0.047258156262526045 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5606936416184971, "acc_stderr": 0.037842719328874674, "acc_norm": 0.5606936416184971, "acc_norm_stderr": 0.037842719328874674 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383887, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383887 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.74, "acc_stderr": 0.0440844002276808, "acc_norm": 0.74, "acc_norm_stderr": 0.0440844002276808 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5148936170212766, "acc_stderr": 0.032671518489247764, "acc_norm": 0.5148936170212766, "acc_norm_stderr": 0.032671518489247764 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4298245614035088, "acc_stderr": 0.046570472605949625, "acc_norm": 0.4298245614035088, "acc_norm_stderr": 0.046570472605949625 }, "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": 0.42328042328042326, "acc_stderr": 0.025446365634406776, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.025446365634406776 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3968253968253968, "acc_stderr": 0.043758884927270605, "acc_norm": 0.3968253968253968, "acc_norm_stderr": 0.043758884927270605 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7290322580645161, "acc_stderr": 0.025284416114900156, "acc_norm": 0.7290322580645161, "acc_norm_stderr": 0.025284416114900156 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.64, "acc_stderr": 0.048241815132442176, "acc_norm": 0.64, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7272727272727273, "acc_stderr": 0.0347769116216366, "acc_norm": 0.7272727272727273, "acc_norm_stderr": 0.0347769116216366 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7777777777777778, "acc_stderr": 0.029620227874790482, "acc_norm": 0.7777777777777778, "acc_norm_stderr": 0.029620227874790482 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8497409326424871, "acc_stderr": 0.025787723180723872, "acc_norm": 0.8497409326424871, "acc_norm_stderr": 0.025787723180723872 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6051282051282051, "acc_stderr": 0.0247843169421564, "acc_norm": 0.6051282051282051, "acc_norm_stderr": 0.0247843169421564 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc
