open-llm-leaderboard-old/details_LeroyDyer__Mixtral_AI_128k
收藏数据集概述
数据集简介
该数据集是在评估模型 LeroyDyer/Mixtral_AI_128k 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
- 创建来源:1 次运行
- 分割方式:每个配置包含特定分割,分割名称使用运行的时间戳。"train" 分割始终指向最新结果。
- 额外配置:"results" 存储所有运行的聚合结果,用于计算和显示聚合指标在 Open LLM Leaderboard 上。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_LeroyDyer__Mixtral_AI_128k", "harness_winogrande_5", split="train")
最新结果
最新结果来自 2024-03-22T00:01:40.502304 运行,包含多个任务的评估结果。以下是部分任务的评估结果示例:
python { "all": { "acc": 0.6414198562803591, "acc_stderr": 0.032426714011595664, "acc_norm": 0.6456775732442286, "acc_norm_stderr": 0.033078273209582204, "mc1": 0.3659730722154223, "mc1_stderr": 0.016862941684088376, "mc2": 0.5242691173246328, "mc2_stderr": 0.015098149499306492 }, "harness|arc:challenge|25": { "acc": 0.5989761092150171, "acc_stderr": 0.014322255790719865, "acc_norm": 0.6322525597269625, "acc_norm_stderr": 0.014090995618168478 }, "harness|hellaswag|10": { "acc": 0.659928301135232, "acc_stderr": 0.004727648057897929, "acc_norm": 0.8462457677753435, "acc_norm_stderr": 0.0035997580435467983 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.04793724854411021, "acc_norm": 0.35, "acc_norm_stderr": 0.04793724854411021 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6296296296296297, "acc_stderr": 0.041716541613545426, "acc_norm": 0.6296296296296297, "acc_norm_stderr": 0.041716541613545426 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6578947368421053, "acc_stderr": 0.038607315993160904, "acc_norm": 0.6578947368421053, "acc_norm_stderr": 0.038607315993160904 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "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": 0.7361111111111112, "acc_stderr": 0.03685651095897532, "acc_norm": 0.7361111111111112, "acc_norm_stderr": 0.03685651095897532 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.49, "acc_stderr": 0.05024183937956911, "acc_norm": 0.49, "acc_norm_stderr": 0.05024183937956911 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.52, "acc_stderr": 0.050211673156867795, "acc_norm": 0.52, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.36, "acc_stderr": 0.048241815132442176, "acc_norm": 0.36, "acc_norm_stderr": 0.048241815132442176 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.653179190751445, "acc_stderr": 0.036291466701596636, "acc_norm": 0.653179190751445, "acc_norm_stderr": 0.036291466701596636 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.43137254901960786, "acc_stderr": 0.04928099597287533, "acc_norm": 0.43137254901960786, "acc_norm_stderr": 0.04928099597287533 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.8, "acc_stderr": 0.04020151261036843, "acc_norm": 0.8, "acc_norm_stderr": 0.04020151261036843 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108101, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108101 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5, "acc_stderr": 0.047036043419179864, "acc_norm": 0.5, "acc_norm_stderr": 0.047036043419179864 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.5517241379310345, "acc_stderr": 0.04144311810878151, "acc_norm": 0.5517241379310345, "acc_norm_stderr": 0.04144311810878151 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.4074074074074074, "acc_stderr": 0.02530590624159063, "acc_norm": 0.4074074074074074, "acc_norm_stderr": 0.02530590624159063 }, "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": 0.7741935483870968, "acc_stderr": 0.023785577884181015, "acc_norm": 0.7741935483870968, "acc_norm_stderr": 0.023785577884181015 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5073891625615764, "acc_stderr": 0.035176035403610105, "acc_norm": 0.5073891625615764, "acc_norm_stderr": 0.035176035403610105 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.68, "acc_stderr": 0.04688261722621505, "acc_norm": 0.68, "acc_norm_stderr": 0.04688261722621505 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7454545454545455, "acc_stderr": 0.03401506715249039, "acc_norm": 0.7454545454545455, "acc_norm_stderr": 0.03401506715249039 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7727272727272727, "acc_stderr": 0.029857515673386417, "acc_norm": 0.7727272727272727, "acc_norm_stderr": 0.029857515673386417 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8808290155440415, "acc_stderr": 0.023381935348121434, "acc_norm": 0.8808290155440415, "acc_norm_stderr": 0.023381935348121434 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6615384615384615, "acc_stderr": 0.023991500500313036, "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.023991500500313036 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.37777777777777777, "acc_stderr": 0.02956070739246571, "acc_norm": 0.37777777777777777, "acc_norm_stderr": 0.02956070739246571 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.680672268907563, "acc_stderr": 0.030283995525884396, "acc_norm": 0.680672268907563, "acc_norm_stderr": 0.030283995525884396 }, "harness|hendrycksTest-high_school_physics|5": { "acc": 0.3509933774834437, "acc_stderr": 0.03896981964257375, "acc_norm": 0.3509933774834437, "acc_norm_stderr": 0.03896981964257375 }, "harness|hendrycksTest-high_school_psychology|5": { "acc": 0.8055045871559633, "acc_stderr": 0.016970289090458033, "acc_norm": 0.8055045871559633, "acc_norm_stderr": 0.016970289090458033 }, "harness|hendrycksTest-high_school_statistics|5": { "acc": 0.5509259259259259, "acc_stderr": 0.03392238405321617, "acc_norm": 0.5509259259259259, "acc_norm_stderr": 0.03392238405321617 }, "harness|hendrycksTest-high_school_us_history|5": { "acc": 0.7843137254901961, "acc_stderr": 0.028867431449849316, "acc_norm": 0.7843137254901961, "acc_norm_stderr": 0.028867431449849316 }, "harness|hendrycksTest-high_school_world_history|5": { "acc": 0.7848101265822784, "acc_stderr": 0.026750826994676173, "acc_norm": 0.7848101265822784, "acc_norm_stderr": 0.026750826994676173 }, "harness|hendrycksTest-human_aging|5": { "acc": 0.6591928251121076, "acc_stderr": 0.0318114974705536, "acc_norm": 0.6591928251121076, "acc_norm_stderr": 0.0318114974705536 }, "harness|hendrycksTest-human_sexuality|5": { "acc": 0.7404580152671756, "acc_stderr": 0.03844876139785271, "acc_norm": 0.7404580152671756, "acc_norm_stderr": 0.03844876139785271 }, "harness|hendrycksTest-international_law|5": { "acc": 0.8099173553719008, "acc_stderr": 0.03581796951709282, "acc_norm": 0.8099173553719008, "acc_norm_stderr": 0.03581796951709282 }, "harness|hendrycksTest-jurisprudence|5": { "acc": 0.7314814814814815, "acc_stderr": 0.042844679680521934, "acc_norm": 0.7314814814814815, "acc_norm_stderr": 0.042844679680521934 }, "harness|hendrycksTest-logical_fallacies|5": { "acc": 0.7914110429447853, "acc_stderr": 0.031921934489347235, "acc_norm": 0.7914110429447853, "acc_norm_stderr": 0.031921934489347235 }, "harness|hendrycksTest-machine_learning|5": { "acc": 0.5267857142857143, "acc_stderr": 0.047389751192741546, "acc_norm": 0.5267857142857143, "acc_norm_stderr": 0.047389751192741546 }, "harness|hendrycksTest-management|5": { "acc": 0.7572815533980582, "acc_stderr": 0.04245022486384495, "acc_norm": 0.7572815533980582, "acc_norm_stderr": 0.04245022486384495 }, "harness|hendrycksTest-marketing|5": { "acc": 0.8632478632478633, "acc_stderr": 0.022509033937077812, "acc_norm": 0.8632478632478633, "acc_norm_stderr": 0.022509033937077812 }, "harness|hendrycksTest-medical_genetics|5": { "acc": 0.75, "acc_stderr": 0.04351941398892446, "acc_norm": 0.75, "acc_norm_stderr": 0.04351941398892446 }, "harness|hendrycksTest-miscellaneous|5": { "acc": 0.8122605363984674, "acc_stderr": 0.013964393769899134, "acc_norm": 0.8122605363984674, "acc_norm_stderr": 0.013964393769899134 }, "harness|hendrycksTest-moral_disputes|5": { "acc": 0.7225433526011561, "acc_stderr": 0.02410571260775431, "acc_norm": 0.7225433526011561, "acc_norm_stderr": 0.02410571260775431 }, "harness|hendrycksTest-moral_scenarios|5": { "acc": 0.3653631284916201, "acc_stderr": 0.01610483388014229, "acc_norm": 0.3653631284916201, "acc_norm_stderr": 0.01610483388014229 }, "harness|hendrycksTest-nutrition|5": { "acc": 0.7418300653594772, "acc_stderr": 0.025058503316958154, "acc_norm": 0.7418300653594772, "acc_norm_stderr": 0.025058503316958154 }, "harness|hendrycksTest-philosophy|5": { "acc": 0.6977491961414791, "acc_stderr": 0.026082700695399665, "acc_norm": 0.6977491961414791, "acc_norm_stderr": 0.026082700695399665 }, "harness|hendrycksTest-prehistory|5": { "acc": 0.7129629629629629, "acc_stderr": 0.02517104191530968, "acc_norm": 0.7129629629629629, "acc_norm_stderr": 0.02517104191530968 }, "harness|hendrycksTest-professional_accounting|5": { "acc": 0.4929078014184397, "acc_stderr": 0.02982449855912901, "acc_norm": 0.4929078014184397, "acc_norm_stderr": 0.02982449855912901 }, "harness|hendrycksTest-professional_law|5": { "acc": 0.4602346805736636, "acc_stderr": 0.012729785386598568, "acc_norm": 0.4602346805736636, "acc_norm_stderr": 0.012729785386598568 }, "harness|hendrycksTest-professional_medicine|5": { "acc": 0.6801470588235294, "acc_stderr": 0.028332959514031218, "acc_norm": 0.6801470588235294, "acc_norm_stderr": 0.028332959514031218 }, "harness|hendrycksTest-professional_psychology|5": { "acc": 0.6601307189542484, "acc_stderr": 0.01916241858862356, "acc_norm": 0.6601307189542484, "acc_norm_stderr": 0.01916241858862356 }, "harness|hendrycksTest-public_relations|5": { "acc": 0.6909090909090909, "acc_stderr": 0.044262946482000985, "acc_norm": 0.6909090909090909, "acc_norm_stderr": 0.044262946482000985 }, "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": 0.8557213930348259, "acc_stderr": 0.024845753212306046, "acc_norm": 0.8557213930348259, "acc_norm_stderr": 0.024845753212306046 }, "harness|hendrycksTest-us_foreign_policy|5": { "acc": 0.88, "acc_stderr": 0.03265986323710905, "acc_norm": 0.88, "acc_norm_stderr": 0.03265986323710905 }, "harness|hendrycksTest-virology|5": { "acc": 0.5481927710843374, "acc_stderr": 0.03874371556587953, "acc_norm": 0.5481927710843374, "acc_norm_stderr": 0.03874371556587953 }, "harness|hendrycksTest-world_religions|5": { "acc": 0.8362573099415205, "acc_stderr": 0.028380919596145866, "acc_norm": 0.8362573099415205, "acc_norm_stderr": 0.028380919596145866 }, "harness|truthfulqa:mc|0": { "mc1": 0.3659730722154223, "mc1_stderr": 0.016862941684088376, "mc2": 0.5242691173246328, "mc2_stderr": 0.015098149499306492 }, "harness|winogrande|5": { "acc": 0.7955801104972375, "acc_stderr": 0.011334090612597207 }, "harness|gsm8k|5": { "acc": 0.45564821834723274, "acc_stderr": 0.013718194542485603 } }
配置详情
-
harness_arc_challenge_25
- 分割:2024_03_22T00_01_40.502304, latest
- 路径:
**/details_harness|arc:challenge|25_2024-03-22T00-01-40.502304.parquet
-
harness_gsm8k_5
- 分割:2024_03_22T00_01_40.502304, latest
- 路径:
**/details_harness|gsm8k|5_2024-03-22T00-01-40.502304.parquet
-
harness_hellaswag_10
- 分割:2024_03_22T00_01_40.502304, latest
- 路径:
**/details_harness|hellaswag|10_2024-03-22T00-01-40.502304.parquet
-
harness_hendrycksTest_5
- 分割:2024_03_22T00_01_40.502304, latest
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-anatomy|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-astronomy|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-business_ethics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-clinical_knowledge|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-college_biology|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-college_chemistry|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-college_computer_science|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-college_mathematics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-college_medicine|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-college_physics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-computer_security|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-conceptual_physics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-econometrics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-electrical_engineering|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-elementary_mathematics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-formal_logic|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-global_facts|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_biology|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_chemistry|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_computer_science|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_european_history|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_geography|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_government_and_politics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_macroeconomics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_mathematics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_microeconomics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_physics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_psychology|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_statistics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_us_history|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-high_school_world_history|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-human_aging|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-human_sexuality|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-international_law|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-jurisprudence|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-logical_fallacies|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-machine_learning|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-management|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-marketing|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-medical_genetics|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-miscellaneous|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-moral_disputes|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-moral_scenarios|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-nutrition|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-philosophy|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-prehistory|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-professional_accounting|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-professional_law|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-professional_medicine|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-professional_psychology|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-public_relations|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-security_studies|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-sociology|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-us_foreign_policy|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-virology|5_2024-03-22T00-01-40.502304.parquet**/details_harness|hendrycksTest-world_religions|5_2024-03-22T00-01-40.502304.parquet



