open-llm-leaderboard-old/details_Azazelle__Mocha-SR-7b-ex
收藏数据集概述
该数据集是在对模型 Azazelle/Mocha-SR-7b-ex 进行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 2 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，用于计算和显示聚合指标在 Open LLM Leaderboard 上。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_Azazelle__Mocha-SR-7b-ex", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-24T19:49:08.397747 运行的最新结果：
python { "all": { "acc": 0.6091398198150786, "acc_stderr": 0.03280906553499857, "acc_norm": 0.6119935223217271, "acc_norm_stderr": 0.033459167863401314, "mc1": 0.3561811505507956, "mc1_stderr": 0.01676379072844634, "mc2": 0.5472145489149565, "mc2_stderr": 0.01603275158736626 }, "harness|arc:challenge|25": { "acc": 0.5742320819112628, "acc_stderr": 0.01444946427886881, "acc_norm": 0.5981228668941979, "acc_norm_stderr": 0.014327268614578273 }, "harness|hellaswag|10": { "acc": 0.6314479187412866, "acc_stderr": 0.004814261966376849, "acc_norm": 0.8123879705238001, "acc_norm_stderr": 0.003896041723166869 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5925925925925926, "acc_stderr": 0.04244633238353227, "acc_norm": 0.5925925925925926, "acc_norm_stderr": 0.04244633238353227 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6710526315789473, "acc_stderr": 0.03823428969926604, "acc_norm": 0.6710526315789473, "acc_norm_stderr": 0.03823428969926604 }, "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": 0.6566037735849056, "acc_stderr": 0.02922452646912479, "acc_norm": 0.6566037735849056, "acc_norm_stderr": 0.02922452646912479 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.75, "acc_stderr": 0.03621034121889507, "acc_norm": 0.75, "acc_norm_stderr": 0.03621034121889507 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.46, "acc_stderr": 0.05009082659620332, "acc_norm": 0.46, "acc_norm_stderr": 0.05009082659620332 }, "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": 0.27, "acc_stderr": 0.044619604333847394, "acc_norm": 0.27, "acc_norm_stderr": 0.044619604333847394 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5838150289017341, "acc_stderr": 0.03758517775404947, "acc_norm": 0.5838150289017341, "acc_norm_stderr": 0.03758517775404947 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.39215686274509803, "acc_stderr": 0.04858083574266344, "acc_norm": 0.39215686274509803, "acc_norm_stderr": 0.04858083574266344 }, "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": 0.49361702127659574, "acc_stderr": 0.03268335899936336, "acc_norm": 0.49361702127659574, "acc_norm_stderr": 0.03268335899936336 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.41228070175438597, "acc_stderr": 0.046306532033665956, "acc_norm": 0.41228070175438597, "acc_norm_stderr": 0.046306532033665956 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5241379310344828, "acc_stderr": 0.0416180850350153, "acc_norm": 0.5241379310344828, "acc_norm_stderr": 0.0416180850350153 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.41534391534391535, "acc_stderr": 0.02537952491077839, "acc_norm": 0.41534391534391535, "acc_norm_stderr": 0.02537952491077839 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4126984126984127, "acc_stderr": 0.04403438954768177, "acc_norm": 0.4126984126984127, "acc_norm_stderr": 0.04403438954768177 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.29, "acc_stderr": 0.04560480215720684, "acc_norm": 0.29, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7322580645161291, "acc_stderr": 0.02518900666021238, "acc_norm": 0.7322580645161291, "acc_norm_stderr": 0.02518900666021238 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.03502544650845872, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.73, "acc_stderr": 0.0446196043338474, "acc_norm": 0.73, "acc_norm_stderr": 0.0446196043338474 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7525252525252525, "acc_stderr": 0.030746300742124498, "acc_norm": 0.7525252525252525, "acc_norm_stderr": 0.030746300742124498 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758716, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758716 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5974358974358974, "acc_stderr": 0.02486499515976775, "acc_norm": 0.5974358974358974, "acc_norm_stderr": 0.02486499515976775 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3111111111111111, "acc_stderr": 0.028226446749683515, "acc_norm": 0.3111111111111111, "acc_norm_stderr": 0.028226446749683515 }, "harness|hendry
