open-llm-leaderboard-old/details_Undi95__Miqu-70B-Alpaca-DPO
收藏数据集概述
数据集来源
该数据集是在评估模型 Undi95/Miqu-70B-Alpaca-DPO 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集结构
- 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_Undi95__Miqu-70B-Alpaca-DPO", "harness_winogrande_5", split="train")
最新结果
以下是 2024-02-10T01:04:42.013037 运行 的最新结果：
python { "all": { "acc": 0.7527317691538201, "acc_stderr": 0.028459884595309796, "acc_norm": 0.7559669786319181, "acc_norm_stderr": 0.029005735780490233, "mc1": 0.5336597307221542, "mc1_stderr": 0.017463793867168103, "mc2": 0.6943559687441003, "mc2_stderr": 0.014805444874590052 }, "harness|arc:challenge|25": { "acc": 0.6928327645051194, "acc_stderr": 0.013481034054980945, "acc_norm": 0.7320819112627986, "acc_norm_stderr": 0.01294203019513643 }, "harness|hellaswag|10": { "acc": 0.7103166699860586, "acc_stderr": 0.004526883021027632, "acc_norm": 0.8859788886675961, "acc_norm_stderr": 0.0031718733502514827 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.7037037037037037, "acc_stderr": 0.03944624162501116, "acc_norm": 0.7037037037037037, "acc_norm_stderr": 0.03944624162501116 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8355263157894737, "acc_stderr": 0.03016753346863271, "acc_norm": 0.8355263157894737, "acc_norm_stderr": 0.03016753346863271 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.8, "acc_stderr": 0.04020151261036844, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036844 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7924528301886793, "acc_stderr": 0.02495991802891127, "acc_norm": 0.7924528301886793, "acc_norm_stderr": 0.02495991802891127 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8958333333333334, "acc_stderr": 0.02554523921025691, "acc_norm": 0.8958333333333334, "acc_norm_stderr": 0.02554523921025691 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.050161355804659205, "acc_norm": 0.53, "acc_norm_stderr": 0.050161355804659205 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.61, "acc_stderr": 0.04902071300001975, "acc_norm": 0.61, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.42, "acc_stderr": 0.04960449637488584, "acc_norm": 0.42, "acc_norm_stderr": 0.04960449637488584 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7514450867052023, "acc_stderr": 0.03295304696818318, "acc_norm": 0.7514450867052023, "acc_norm_stderr": 0.03295304696818318 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4803921568627451, "acc_stderr": 0.04971358884367406, "acc_norm": 0.4803921568627451, "acc_norm_stderr": 0.04971358884367406 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.84, "acc_stderr": 0.03684529491774709, "acc_norm": 0.84, "acc_norm_stderr": 0.03684529491774709 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7361702127659574, "acc_stderr": 0.028809989854102956, "acc_norm": 0.7361702127659574, "acc_norm_stderr": 0.028809989854102956 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5964912280701754, "acc_stderr": 0.04615186962583707, "acc_norm": 0.5964912280701754, "acc_norm_stderr": 0.04615186962583707 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7310344827586207, "acc_stderr": 0.036951833116502325, "acc_norm": 0.7310344827586207, "acc_norm_stderr": 0.036951833116502325 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.5555555555555556, "acc_stderr": 0.025591857761382186, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.025591857761382186 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5555555555555556, "acc_stderr": 0.04444444444444449, "acc_norm": 0.5555555555555556, "acc_norm_stderr": 0.04444444444444449 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.49, "acc_stderr": 0.05024183937956913, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956913 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.864516129032258, "acc_stderr": 0.019469334586486933, "acc_norm": 0.864516129032258, "acc_norm_stderr": 0.019469334586486933 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6354679802955665, "acc_stderr": 0.0338640574606209, "acc_norm": 0.6354679802955665, "acc_norm_stderr": 0.0338640574606209 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.87, "acc_stderr": 0.03379976689896309, "acc_norm": 0.87, "acc_norm_stderr": 0.03379976689896309 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8424242424242424, "acc_stderr": 0.028450388805284357, "acc_norm": 0.8424242424242424, "acc_norm_stderr": 0.028450388805284357 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9040404040404041, "acc_stderr": 0.020984808610047933, "acc_norm": 0.9040404040404041, "acc_norm_stderr": 0.020984808610047933 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9430051813471503, "acc_stderr": 0.016731085293607558, "acc_norm": 0.9430051813471503, "acc_norm_stderr": 0.016731085293607558 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.7897435897435897, "acc_stderr": 0.020660597485026938, "acc_norm": 0.7897435897435897, "acc_norm_stderr": 0.020660597485026938 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.4222222222222222, "acc_stderr": 0.030114442019668092, "acc_norm": 0.422222222
