open-llm-leaderboard-old/details_NotAiLOL__Boundary-Coder-Yi-2x6B-MoE
收藏数据集概述
该数据集是在对模型 NotAiLOL/Boundary-Coder-Yi-2x6B-MoE 进行评估运行期间自动创建的，评估运行在 Open LLM Leaderboard 上进行。
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_NotAiLOL__Boundary-Coder-Yi-2x6B-MoE", "harness_winogrande_5", split="train")
最新结果
以下是 2024-04-23T04:26:32.725811 运行的最新结果：
python { "all": { "acc": 0.6351914135197708, "acc_stderr": 0.032134461499373365, "acc_norm": 0.6440300515382569, "acc_norm_stderr": 0.03279447953874105, "mc1": 0.3537331701346389, "mc1_stderr": 0.016737814358846147, "mc2": 0.49820032746376186, "mc2_stderr": 0.015928270445063328 }, "harness|arc:challenge|25": { "acc": 0.5315699658703071, "acc_stderr": 0.014582236460866977, "acc_norm": 0.568259385665529, "acc_norm_stderr": 0.014474591427196202 }, "harness|hellaswag|10": { "acc": 0.5924118701453893, "acc_stderr": 0.0049038158859832795, "acc_norm": 0.7816172077275443, "acc_norm_stderr": 0.004123042199101581 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "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": 0.6973684210526315, "acc_stderr": 0.03738520676119667, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119667 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.71, "acc_stderr": 0.04560480215720684, "acc_norm": 0.71, "acc_norm_stderr": 0.04560480215720684 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6867924528301886, "acc_stderr": 0.028544793319055326, "acc_norm": 0.6867924528301886, "acc_norm_stderr": 0.028544793319055326 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6875, "acc_stderr": 0.038760854559127644, "acc_norm": 0.6875, "acc_norm_stderr": 0.038760854559127644 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.45, "acc_stderr": 0.05, "acc_norm": 0.45, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.54, "acc_stderr": 0.05009082659620332, "acc_norm": 0.54, "acc_norm_stderr": 0.05009082659620332 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.33, "acc_stderr": 0.04725815626252606, "acc_norm": 0.33, "acc_norm_stderr": 0.04725815626252606 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247078, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247078 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.37254901960784315, "acc_stderr": 0.04810840148082636, "acc_norm": 0.37254901960784315, "acc_norm_stderr": 0.04810840148082636 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816507, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816507 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.6042553191489362, "acc_stderr": 0.031967586978353606, "acc_norm": 0.6042553191489362, "acc_norm_stderr": 0.031967586978353606 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.40350877192982454, "acc_stderr": 0.046151869625837026, "acc_norm": 0.40350877192982454, "acc_norm_stderr": 0.046151869625837026 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6344827586206897, "acc_stderr": 0.040131241954243856, "acc_norm": 0.6344827586206897, "acc_norm_stderr": 0.040131241954243856 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4656084656084656, "acc_stderr": 0.025690321762493838, "acc_norm": 0.4656084656084656, "acc_norm_stderr": 0.025690321762493838 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.4365079365079365, "acc_stderr": 0.04435932892851466, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.04435932892851466 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7677419354838709, "acc_stderr": 0.024022256130308235, "acc_norm": 0.7677419354838709, "acc_norm_stderr": 0.024022256130308235 }, "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": 0.67, "acc_stderr": 0.04725815626252607, "acc_norm": 0.67, "acc_norm_stderr": 0.04725815626252607 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7515151515151515, "acc_stderr": 0.033744026441394036, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.033744026441394036 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8232323232323232, "acc_stderr": 0.027178752639044915, "acc_norm": 0.8232323232323232, "acc_norm_stderr": 0.027178752639044915 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9067357512953368, "acc_stderr": 0.0209868545932897, "acc_norm": 0.9067357512953368, "acc_norm_stderr": 0.0209868545932897 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.02394672474156397, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.02394672474156397 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.34074074074074073, "acc_stderr": 0.028897748741131137, "acc_norm": 0.34074074074074073, "acc_norm_stderr": 0.02889774874113113
