open-llm-leaderboard-old/details_silvercoder45__Mistral-7b-instruct-v0.2-summ-sft-dpo-e1
收藏数据集概述
数据集摘要
该数据集是在对模型 silvercoder45/Mistral-7b-instruct-v0.2-summ-sft-dpo-e1 进行评估运行时自动创建的,用于 Open LLM Leaderboard。
数据集组成
- 该数据集包含 63 个配置,每个配置对应一个评估任务。
- 数据集来自 1 次运行,每次运行在每个配置中都有一个特定的分割,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_silvercoder45__Mistral-7b-instruct-v0.2-summ-sft-dpo-e1", "harness_winogrande_5", split="train")
最新结果
以下是 2024-01-22T09:52:31.786673 运行的最新结果:
python { "all": { "acc": 0.6062600204892812, "acc_stderr": 0.03315436827084122, "acc_norm": 0.6105005647485784, "acc_norm_stderr": 0.033825828468753205, "mc1": 0.5605875152998776, "mc1_stderr": 0.017374520482513707, "mc2": 0.7076437205804561, "mc2_stderr": 0.015031924672941057 }, "harness|arc:challenge|25": { "acc": 0.5930034129692833, "acc_stderr": 0.01435639941800912, "acc_norm": 0.6271331058020477, "acc_norm_stderr": 0.014131176760131172 }, "harness|hellaswag|10": { "acc": 0.6742680740888269, "acc_stderr": 0.004676898861978911, "acc_norm": 0.8530173272256523, "acc_norm_stderr": 0.003533649851728493 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.31, "acc_stderr": 0.04648231987117316, "acc_norm": 0.31, "acc_norm_stderr": 0.04648231987117316 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.5851851851851851, "acc_stderr": 0.04256193767901408, "acc_norm": 0.5851851851851851, "acc_norm_stderr": 0.04256193767901408 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.618421052631579, "acc_stderr": 0.039531733777491945, "acc_norm": 0.618421052631579, "acc_norm_stderr": 0.039531733777491945 }, "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": 0.6754716981132075, "acc_stderr": 0.02881561571343211, "acc_norm": 0.6754716981132075, "acc_norm_stderr": 0.02881561571343211 }, "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": 0.049236596391733084, "acc_norm": 0.4, "acc_norm_stderr": 0.049236596391733084 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.38, "acc_stderr": 0.04878317312145632, "acc_norm": 0.38, "acc_norm_stderr": 0.04878317312145632 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5953757225433526, "acc_stderr": 0.03742461193887248, "acc_norm": 0.5953757225433526, "acc_norm_stderr": 0.03742461193887248 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.4117647058823529, "acc_stderr": 0.04897104952726367, "acc_norm": 0.4117647058823529, "acc_norm_stderr": 0.04897104952726367 }, "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": 0.5234042553191489, "acc_stderr": 0.03265019475033582, "acc_norm": 0.5234042553191489, "acc_norm_stderr": 0.03265019475033582 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.42105263157894735, "acc_stderr": 0.046446020912223177, "acc_norm": 0.42105263157894735, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6068965517241379, "acc_stderr": 0.0407032901370707, "acc_norm": 0.6068965517241379, "acc_norm_stderr": 0.0407032901370707 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.3835978835978836, "acc_stderr": 0.0250437573185202, "acc_norm": 0.3835978835978836, "acc_norm_stderr": 0.0250437573185202 }, "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": 0.603225806451613, "acc_stderr": 0.027831231605767948, "acc_norm": 0.603225806451613, "acc_norm_stderr": 0.027831231605767948 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5123152709359606, "acc_stderr": 0.035169204442208966, "acc_norm": 0.5123152709359606, "acc_norm_stderr": 0.035169204442208966 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.62, "acc_stderr": 0.04878317312145632, "acc_norm": 0.62, "acc_norm_stderr": 0.04878317312145632 }, "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": 0.7474747474747475, "acc_stderr": 0.03095405547036589, "acc_norm": 0.7474747474747475, "acc_norm_stderr": 0.03095405547036589 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8549222797927462, "acc_stderr": 0.025416343096306443, "acc_norm": 0.8549222797927462, "acc_norm_stderr": 0.025416343096306443 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5743589743589743, "acc_stderr": 0.025069094387296532, "acc_norm": 0.5743589743589743, "acc_norm_stderr": 0.025069094387296532 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.29259259259259257, "acc_stderr": 0.027738969632176085, "acc_norm": 0.29259259259259257, "acc_norm_stderr": 0.027738969632176085 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.6722689075630253, "acc_stderr": 0.030489911417673227, "acc_norm": 0.6722689075630253, "acc_norm_stderr": 0.030489911417673227 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.33774834437086093, "acc_stderr": 0.0386155754625517, "acc_norm": 0.33774834437086093, "acc_norm_stderr": 0.0386155754625517 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.7889908256880734, "acc_stderr": 0.01749392240411265, "acc_norm": 0.7889908256880734, "acc_norm_stderr": 0.01749392240411265 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.4398148148148148, "acc_stderr": 0.03385177976044811, "acc_norm": 0.4398148148148148, "acc_norm_stderr": 0.03385177976044811 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.7794117647058824, "acc_stderr": 0.02910225438967407, "acc_norm": 0.7794117647058824, "acc_norm_stderr": 0.02910225438967407 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.759493670886076, "acc_stderr": 0.02782078198114969, "acc_norm": 0.759493670886076, "acc_norm_stderr": 0.02782078198114969 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6188340807174888, "acc_stderr": 0.03259625118416827, "acc_norm": 0.6188340807174888, "acc_norm_stderr": 0.03259625118416827 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7251908396946565, "acc_stderr": 0.03915345408847836, "acc_norm": 0.7251908396946565, "acc_norm_stderr": 0.03915345408847836 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8016528925619835, "acc_stderr": 0.03640118271990947, "acc_norm": 0.8016528925619835, "acc_norm_stderr": 0.03640118271990947 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7407407407407407, "acc_stderr": 0.042365112580946336, "acc_norm": 0.7407407407407407, "acc_norm_stderr": 0.042365112580946336 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7423312883435583, "acc_stderr": 0.03436150827846917, "acc_norm": 0.7423312883435583, "acc_norm_stderr": 0.03436150827846917 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.4642857142857143, "acc_stderr": 0.04733667890053756, "acc_norm": 0.4642857142857143, "acc_norm_stderr": 0.04733667890053756 }, "harness|hendrycksTest-management|5": { "acc": 0.7378640776699029, "acc_stderr": 0.04354631077260594, "acc_norm": 0.7378640776699029, "acc_norm_stderr": 0.04354631077260594 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8675213675213675, "acc_stderr": 0.022209309073165612, "acc_norm": 0.8675213675213675, "acc_norm_stderr": 0.022209309073165612 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.68, "acc_stderr": 0.046882617226215034, "acc_norm": 0.68, "acc_norm_stderr": 0.046882617226215034 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.7816091954022989, "acc_stderr": 0.014774358319934486, "acc_norm": 0.7816091954022989, "acc_norm_stderr": 0.014774358319934486 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.6878612716763006, "acc_stderr": 0.024946792225272314, "acc_norm": 0.6878612716763006, "acc_norm_stderr": 0.024946792225272314 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.29720670391061454, "acc_stderr": 0.015285313353641602, "acc_norm": 0.29720670391061454, "acc_norm_stderr": 0.015285313353641602 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.6764705882352942, "acc_stderr": 0.026787453111906508, "acc_norm": 0.6764705882352942, "acc_norm_stderr": 0.026787453111906508 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.6977491961414791, "acc_stderr": 0.02608270069539966, "acc_norm": 0.6977491961414791, "acc_norm_stderr": 0.02608270069539966 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.6944444444444444, "acc_stderr": 0.025630824975621344, "acc_norm": 0.6944444444444444, "acc_norm_stderr": 0.025630824975621344 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.4716312056737589, "acc_stderr": 0.029779450957303062, "acc_norm": 0.4716312056737589, "acc_norm_stderr": 0.029779450957303062 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4361147327249022, "acc_stderr": 0.012665568135455333, "acc_norm": 0.4361147327249022, "acc_norm_stderr": 0.012665568135455333 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6213235294117647, "acc_stderr": 0.02946513363977613, "acc_norm": 0.6213235294117647, "acc_norm_stderr": 0.02946513363977613 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.630718954248366, "acc_stderr": 0.019524316744866356, "acc_norm": 0.630718954248366, "acc_norm_stderr": 0.019524316744866356 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.7181818181818181, "acc_stderr": 0.043091187099464585, "acc_norm": 0.7181818181818181, "acc_norm_stderr": 0.043091187099464585 }, "harness|hendrycksTest-security_studies|5": { "acc": 0.7183673469387755, "acc_stderr": 0.028795185574291293, "acc_norm": 0.7183673469387755, "acc_norm_stderr": 0.028795185574291293 }, "harness|hendrycksTest-sociology|5": { "acc": 0.7014925373134329, "acc_stderr": 0.032357437893550424, "acc_norm": 0.7014925373134329, "acc_norm_stderr": 0.032357437893550424 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.81, "acc_stderr": 0.039427724440366255, "acc_norm": 0.81, "acc_norm_stderr": 0.039427724440366255 }, "harness|hendrycksTest-virology|5": { "acc": 0.4939759036144578, "acc_stderr": 0.03892212195333047, "acc_norm": 0.4939759036144578, "acc_norm_stderr": 0.03892212195333047 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8245614035087719, "acc_stderr": 0.02917088550072767, "acc_norm": 0.8245614035087719, "acc_norm_stderr": 0.02917088550072767 }, "harness|truthfulqa:mc|0": { "mc1": 0.5605875152998776, "mc1_stderr": 0.017374520482513707, "mc2": 0.7076437205804561, "mc2_stderr": 0.015031924672941057 }, "harness|winogrande|5": { "acc": 0.771112865035517, "acc_stderr": 0.01180736022402539 }, "harness|gsm8k|5": { "acc": 0.4040940106141016, "acc_stderr": 0.013516752972721717 } }



