open-llm-leaderboard-old/details_SanjiWatsuki__neural-chat-7b-v3-3-wizardmath-dare-me
收藏数据集概述
该数据集是在对模型 SanjiWatsuki/neural-chat-7b-v3-3-wizardmath-dare-me 进行评估运行时自动创建的，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_SanjiWatsuki__neural-chat-7b-v3-3-wizardmath-dare-me", "harness_winogrande_5", split="train")
最新结果
以下是 2023-12-27T13:07:52.569856 运行 的最新结果：
python { "all": { "acc": 0.5841627607476706, "acc_stderr": 0.03324720041632836, "acc_norm": 0.5857534686922531, "acc_norm_stderr": 0.03390900076414602, "mc1": 0.4504283965728274, "mc1_stderr": 0.017417264371967646, "mc2": 0.6260346176960404, "mc2_stderr": 0.01578574508599339 }, "harness|arc:challenge|25": { "acc": 0.5588737201365188, "acc_stderr": 0.014509747749064664, "acc_norm": 0.5964163822525598, "acc_norm_stderr": 0.014337158914268447 }, "harness|hellaswag|10": { "acc": 0.6515634335789683, "acc_stderr": 0.004755013243022125, "acc_norm": 0.8263294164509062, "acc_norm_stderr": 0.0037805175193024827 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.22, "acc_stderr": 0.041633319989322695, "acc_norm": 0.22, "acc_norm_stderr": 0.041633319989322695 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.562962962962963, "acc_stderr": 0.04284958639753401, "acc_norm": 0.562962962962963, "acc_norm_stderr": 0.04284958639753401 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.03860731599316091, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.03860731599316091 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.049236596391733084, "acc_norm": 0.6, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6339622641509434, "acc_stderr": 0.029647813539365245, "acc_norm": 0.6339622641509434, "acc_norm_stderr": 0.029647813539365245 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6527777777777778, "acc_stderr": 0.039812405437178615, "acc_norm": 0.6527777777777778, "acc_norm_stderr": 0.039812405437178615 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.04975698519562427, "acc_norm": 0.43, "acc_norm_stderr": 0.04975698519562427 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.050161355804659205, "acc_norm": 0.47, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252604, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252604 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6011560693641619, "acc_stderr": 0.037336266553835096, "acc_norm": 0.6011560693641619, "acc_norm_stderr": 0.037336266553835096 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082635, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082635 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.7, "acc_stderr": 0.046056618647183814, "acc_norm": 0.7, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4978723404255319, "acc_stderr": 0.03268572658667492, "acc_norm": 0.4978723404255319, "acc_norm_stderr": 0.03268572658667492 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.35964912280701755, "acc_stderr": 0.04514496132873633, "acc_norm": 0.35964912280701755, "acc_norm_stderr": 0.04514496132873633 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.4827586206896552, "acc_stderr": 0.04164188720169377, "acc_norm": 0.4827586206896552, "acc_norm_stderr": 0.04164188720169377 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3386243386243386, "acc_stderr": 0.02437319786798306, "acc_norm": 0.3386243386243386, "acc_norm_stderr": 0.02437319786798306 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.3333333333333333, "acc_stderr": 0.04216370213557835, "acc_norm": 0.3333333333333333, "acc_norm_stderr": 0.04216370213557835 }, "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": 0.6870967741935484, "acc_stderr": 0.02637756702864586, "acc_norm": 0.6870967741935484, "acc_norm_stderr": 0.02637756702864586 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.39408866995073893, "acc_stderr": 0.03438157967036545, "acc_norm": 0.39408866995073893, "acc_norm_stderr": 0.03438157967036545 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.66, "acc_stderr": 0.04760952285695237, "acc_norm": 0.66, "acc_norm_stderr": 0.04760952285695237 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7151515151515152, "acc_stderr": 0.03524390844511781, "acc_norm": 0.7151515151515152, "acc_norm_stderr": 0.03524390844511781 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7222222222222222, "acc_stderr": 0.03191178226713548, "acc_norm": 0.7222222222222222, "acc_norm_stderr": 0.03191178226713548 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8704663212435233, "acc_stderr": 0.024233532297758733, "acc_norm": 0.8704663212435233, "acc_norm_stderr": 0.024233532297758733 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5615384615384615, "acc_stderr": 0.025158266016868578, "acc_norm": 0.5615384615384615, "acc_norm_stderr": 0.025158266016868578 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.28888888888888886, "acc_stderr": 0.0276349
