open-llm-leaderboard-old/details_codemateai__CodeMate-v0.1
收藏数据集概述
数据集简介
该数据集是在对模型 codemateai/CodeMate-v0.1 进行评估运行期间自动创建的，评估结果发布在 Open LLM Leaderboard 上。
数据集结构
- 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，每次运行的详细结果可以在每个配置中找到，以运行的时间戳命名的特定分片形式存储。
- "train" 分片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，用于计算和显示在 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_codemateai__CodeMate-v0.1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-21T06:09:28.269211 运行的最新结果：
python { "all": { "acc": 0.5539633133523945, "acc_stderr": 0.03410596348207958, "acc_norm": 0.5569723735975259, "acc_norm_stderr": 0.03480720286888438, "mc1": 0.3268053855569155, "mc1_stderr": 0.01641987473113503, "mc2": 0.4864060014239976, "mc2_stderr": 0.015446552144630315 }, "harness|arc:challenge|25": { "acc": 0.5452218430034129, "acc_stderr": 0.014551507060836359, "acc_norm": 0.5554607508532423, "acc_norm_stderr": 0.01452122640562708 }, "harness|hellaswag|10": { "acc": 0.5930093606851224, "acc_stderr": 0.004902690765066425, "acc_norm": 0.7803226448914559, "acc_norm_stderr": 0.004131818797713872 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.4222222222222222, "acc_stderr": 0.04266763404099582, "acc_norm": 0.4222222222222222, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.5657894736842105, "acc_stderr": 0.040335656678483205, "acc_norm": 0.5657894736842105, "acc_norm_stderr": 0.040335656678483205 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.5132075471698113, "acc_stderr": 0.030762134874500476, "acc_norm": 0.5132075471698113, "acc_norm_stderr": 0.030762134874500476 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.5486111111111112, "acc_stderr": 0.041614023984032786, "acc_norm": 0.5486111111111112, "acc_norm_stderr": 0.041614023984032786 }, "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": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.47398843930635837, "acc_stderr": 0.03807301726504511, "acc_norm": 0.47398843930635837, "acc_norm_stderr": 0.03807301726504511 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3137254901960784, "acc_stderr": 0.04617034827006717, "acc_norm": 0.3137254901960784, "acc_norm_stderr": 0.04617034827006717 }, "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": 0.502127659574468, "acc_stderr": 0.032685726586674915, "acc_norm": 0.502127659574468, "acc_norm_stderr": 0.032685726586674915 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.04615186962583703, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.04615186962583703 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.496551724137931, "acc_stderr": 0.04166567577101579, "acc_norm": 0.496551724137931, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.42328042328042326, "acc_stderr": 0.02544636563440677, "acc_norm": 0.42328042328042326, "acc_norm_stderr": 0.02544636563440677 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4603174603174603, "acc_stderr": 0.04458029125470973, "acc_norm": 0.4603174603174603, "acc_norm_stderr": 0.04458029125470973 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6, "acc_stderr": 0.027869320571664632, "acc_norm": 0.6, "acc_norm_stderr": 0.027869320571664632 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4088669950738916, "acc_stderr": 0.034590588158832314, "acc_norm": 0.4088669950738916, "acc_norm_stderr": 0.034590588158832314 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.74, "acc_stderr": 0.04408440022768078, "acc_norm": 0.74, "acc_norm_stderr": 0.04408440022768078 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6848484848484848, "acc_stderr": 0.0362773057502241, "acc_norm": 0.6848484848484848, "acc_norm_stderr": 0.0362773057502241 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.702020202020202, "acc_stderr": 0.03258630383836557, "acc_norm": 0.702020202020202, "acc_norm_stderr": 0.03258630383836557 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.7668393782383419, "acc_stderr": 0.03051611137147601, "acc_norm": 0.7668393782383419, "acc_norm_stderr": 0.03051611137147601 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5282051282051282, "acc_stderr": 0.025310639254933882, "acc_norm": 0.5282051282051282, "acc_norm_stderr": 0.025310639254933882 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.2851851851851852, "acc_stderr": 0.027528599210340492, "acc_norm": 0.2851851851851852, "acc_norm_stderr": 0.027528599210340492 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc":
