open-llm-leaderboard-old/details_Walmart-the-bag__Yi-6B-Infinity-Chat
收藏数据集概述
该数据集是在评估模型Walmart-the-bag/Yi-6B-Infinity-Chat在Open LLM Leaderboard上的自动创建的。数据集包含63个配置，每个配置对应一个评估任务。
数据集结构
- 配置数量：63个配置
- 数据来源：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。
- 最新结果："train"分割始终指向最新结果。
- 结果汇总：一个额外的配置"results"存储所有运行的汇总结果，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_Walmart-the-bag__Yi-6B-Infinity-Chat", "harness_winogrande_5", split="train")
最新结果
以下是2023-12-27T12:43:24.987428的最新结果：
python { "all": { "acc": 0.6349062046421136, "acc_stderr": 0.03216959197766624, "acc_norm": 0.641573735628457, "acc_norm_stderr": 0.03281243961732792, "mc1": 0.35128518971848227, "mc1_stderr": 0.0167113581635444, "mc2": 0.5074966311746293, "mc2_stderr": 0.01566752376256644 }, "harness|arc:challenge|25": { "acc": 0.5315699658703071, "acc_stderr": 0.014582236460866978, "acc_norm": 0.5656996587030717, "acc_norm_stderr": 0.01448470304885736 }, "harness|hellaswag|10": { "acc": 0.5875323640709023, "acc_stderr": 0.004912723848944794, "acc_norm": 0.7766381198964349, "acc_norm_stderr": 0.0041564771409096125 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.34, "acc_stderr": 0.04760952285695235, "acc_norm": 0.34, "acc_norm_stderr": 0.04760952285695235 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6444444444444445, "acc_stderr": 0.04135176749720385, "acc_norm": 0.6444444444444445, "acc_norm_stderr": 0.04135176749720385 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.7105263157894737, "acc_stderr": 0.03690677986137282, "acc_norm": 0.7105263157894737, "acc_norm_stderr": 0.03690677986137282 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6943396226415094, "acc_stderr": 0.028353298073322663, "acc_norm": 0.6943396226415094, "acc_norm_stderr": 0.028353298073322663 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6736111111111112, "acc_stderr": 0.03921067198982266, "acc_norm": 0.6736111111111112, "acc_norm_stderr": 0.03921067198982266 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.05, "acc_norm": 0.55, "acc_norm_stderr": 0.05 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.3, "acc_stderr": 0.046056618647183814, "acc_norm": 0.3, "acc_norm_stderr": 0.046056618647183814 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6647398843930635, "acc_stderr": 0.03599586301247077, "acc_norm": 0.6647398843930635, "acc_norm_stderr": 0.03599586301247077 }, "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": 0.5957446808510638, "acc_stderr": 0.03208115750788684, "acc_norm": 0.5957446808510638, "acc_norm_stderr": 0.03208115750788684 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.3684210526315789, "acc_stderr": 0.04537815354939392, "acc_norm": 0.3684210526315789, "acc_norm_stderr": 0.04537815354939392 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.04028731532947558, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.04028731532947558 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4365079365079365, "acc_stderr": 0.02554284681740048, "acc_norm": 0.4365079365079365, "acc_norm_stderr": 0.02554284681740048 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42063492063492064, "acc_stderr": 0.04415438226743744, "acc_norm": 0.42063492063492064, "acc_norm_stderr": 0.04415438226743744 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.39, "acc_stderr": 0.04902071300001974, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001974 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7774193548387097, "acc_stderr": 0.02366421667164251, "acc_norm": 0.7774193548387097, "acc_norm_stderr": 0.02366421667164251 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5024630541871922, "acc_stderr": 0.03517945038691063, "acc_norm": 0.5024630541871922, "acc_norm_stderr": 0.03517945038691063 }, "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": 0.03374402644139403, "acc_norm": 0.7515151515151515, "acc_norm_stderr": 0.03374402644139403 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8282828282828283, "acc_stderr": 0.02686971618742991, "acc_norm": 0.8282828282828283, "acc_norm_stderr": 0.02686971618742991 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033456, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033456 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6641025641025641, "acc_stderr": 0.023946724741563966, "acc_norm": 0.6641025641025641, "acc_norm_stderr": 0.023946724741563966 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3074074074074074, "acc_stderr": 0.028133252578815635, "acc_norm": 0.3074074074074074, "acc_norm_stderr": 0.028133252578815635 },
