open-llm-leaderboard-old/details_wang7776__Mistral-7B-Instruct-v0.2-attention-sparsity-20
收藏数据集概述
数据集名称
Evaluation run of wang7776/Mistral-7B-Instruct-v0.2-attention-sparsity-20
数据集描述
该数据集是在对模型 wang7776/Mistral-7B-Instruct-v0.2-attention-sparsity-20 进行评估运行时自动创建的，用于 Open LLM Leaderboard。
数据集结构
- 配置数量：63个配置，每个配置对应一个评估任务。
- 运行次数：数据集从1次运行中创建。每个运行在每个配置中作为一个特定的分割存在，分割名称使用运行的时间戳。
- 分割：每个配置中的 "train" 分割始终指向最新的结果。
- 结果配置：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_wang7776__Mistral-7B-Instruct-v0.2-attention-sparsity-20", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-25T20:11:05.544103 运行 的最新结果：
python { "all": { "acc": 0.6080107405407549, "acc_stderr": 0.033123570691062657, "acc_norm": 0.6125186012133447, "acc_norm_stderr": 0.033796374202489106, "mc1": 0.5348837209302325, "mc1_stderr": 0.017460849975873972, "mc2": 0.6826355141109229, "mc2_stderr": 0.015165454014454297 }, "harness|arc:challenge|25": { "acc": 0.5827645051194539, "acc_stderr": 0.014409825518403082, "acc_norm": 0.628839590443686, "acc_norm_stderr": 0.014117971901142825 }, "harness|hellaswag|10": { "acc": 0.6682931686914957, "acc_stderr": 0.004698640688271199, "acc_norm": 0.8484365664210317, "acc_norm_stderr": 0.003578643387547847 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.32, "acc_stderr": 0.046882617226215034, "acc_norm": 0.32, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5777777777777777, "acc_stderr": 0.04266763404099582, "acc_norm": 0.5777777777777777, "acc_norm_stderr": 0.04266763404099582 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6447368421052632, "acc_stderr": 0.038947344870133176, "acc_norm": 0.6447368421052632, "acc_norm_stderr": 0.038947344870133176 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.04943110704237102, "acc_norm": 0.59, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6679245283018868, "acc_stderr": 0.028985455652334388, "acc_norm": 0.6679245283018868, "acc_norm_stderr": 0.028985455652334388 }, "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": 0.4, "acc_stderr": 0.04923659639173309, "acc_norm": 0.4, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.49, "acc_stderr": 0.05024183937956912, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.049604496374885836, "acc_norm": 0.42, "acc_norm_stderr": 0.049604496374885836 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5780346820809249, "acc_stderr": 0.0376574669386515, "acc_norm": 0.5780346820809249, "acc_norm_stderr": 0.0376574669386515 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4215686274509804, "acc_stderr": 0.04913595201274498, "acc_norm": 0.4215686274509804, "acc_norm_stderr": 0.04913595201274498 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.69, "acc_stderr": 0.04648231987117316, "acc_norm": 0.69, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5276595744680851, "acc_stderr": 0.03263597118409769, "acc_norm": 0.5276595744680851, "acc_norm_stderr": 0.03263597118409769 }, "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": 0.6275862068965518, "acc_stderr": 0.04028731532947558, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.04028731532947558 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3862433862433862, "acc_stderr": 0.025075981767601688, "acc_norm": 0.3862433862433862, "acc_norm_stderr": 0.025075981767601688 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.42857142857142855, "acc_stderr": 0.0442626668137991, "acc_norm": 0.42857142857142855, "acc_norm_stderr": 0.0442626668137991 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.36, "acc_stderr": 0.04824181513244218, "acc_norm": 0.36, "acc_norm_stderr": 0.04824181513244218 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6387096774193548, "acc_stderr": 0.02732754844795754, "acc_norm": 0.6387096774193548, "acc_norm_stderr": 0.02732754844795754 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.4876847290640394, "acc_stderr": 0.035169204442208966, "acc_norm": 0.4876847290640394, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.63, "acc_stderr": 0.04852365870939099, "acc_norm": 0.63, "acc_norm_stderr": 0.04852365870939099 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7676767676767676, "acc_stderr": 0.030088629490217487, "acc_norm": 0.7676767676767676, "acc_norm_stderr": 0.030088629490217487 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8393782383419689, "acc_stderr": 0.026499057701397443, "acc_norm": 0.8393782383419689, "acc_norm_stderr": 0.026499057701397443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5692307692307692, "acc_stderr": 0.025106820660539753, "acc_norm": 0.5692307692307692, "acc_norm_stderr": 0.025106820660539753 }, "harness|hendrycksTest-high_school_mathematics|5": {
