open-llm-leaderboard-old/details_Azure99__blossom-v5-34b
收藏数据集概述
该数据集是在对模型 Azure99/blossom-v5-34b 进行评估运行期间自动创建的，用于 Open LLM Leaderboard。
数据集组成
- 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。
- 额外的 "results" 配置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_Azure99__blossom-v5-34b", "harness_winogrande_5", split="train")
最新结果
以下是 2024-03-14T20:57:30.186390 运行的最新结果：
python { "all": { "acc": 0.7552201167135215, "acc_stderr": 0.028395864629516963, "acc_norm": 0.7599761863011391, "acc_norm_stderr": 0.028930201254559158, "mc1": 0.45165238678090575, "mc1_stderr": 0.017421480300277643, "mc2": 0.6267772016923179, "mc2_stderr": 0.015114233053155776 }, "harness|arc:challenge|25": { "acc": 0.6407849829351536, "acc_stderr": 0.014020224155839159, "acc_norm": 0.6697952218430034, "acc_norm_stderr": 0.013743085603760424 }, "harness|hellaswag|10": { "acc": 0.6523600876319459, "acc_stderr": 0.004752476997887818, "acc_norm": 0.8479386576379208, "acc_norm_stderr": 0.0035834648107534784 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.5, "acc_stderr": 0.050251890762960605, "acc_norm": 0.5, "acc_norm_stderr": 0.050251890762960605 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.725925925925926, "acc_stderr": 0.03853254836552003, "acc_norm": 0.725925925925926, "acc_norm_stderr": 0.03853254836552003 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.8881578947368421, "acc_stderr": 0.025648341251693598, "acc_norm": 0.8881578947368421, "acc_norm_stderr": 0.025648341251693598 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.76, "acc_stderr": 0.04292346959909283, "acc_norm": 0.76, "acc_norm_stderr": 0.04292346959909283 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7811320754716982, "acc_stderr": 0.0254478638251086, "acc_norm": 0.7811320754716982, "acc_norm_stderr": 0.0254478638251086 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.875, "acc_stderr": 0.02765610492929436, "acc_norm": 0.875, "acc_norm_stderr": 0.02765610492929436 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.53, "acc_stderr": 0.05016135580465919, "acc_norm": 0.53, "acc_norm_stderr": 0.05016135580465919 }, "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": 0.41, "acc_stderr": 0.049431107042371025, "acc_norm": 0.41, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.7283236994219653, "acc_stderr": 0.03391750322321659, "acc_norm": 0.7283236994219653, "acc_norm_stderr": 0.03391750322321659 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.49019607843137253, "acc_stderr": 0.04974229460422817, "acc_norm": 0.49019607843137253, "acc_norm_stderr": 0.04974229460422817 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.82, "acc_stderr": 0.03861229196653695, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653695 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7617021276595745, "acc_stderr": 0.027851252973889778, "acc_norm": 0.7617021276595745, "acc_norm_stderr": 0.027851252973889778 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.5789473684210527, "acc_stderr": 0.046446020912223177, "acc_norm": 0.5789473684210527, "acc_norm_stderr": 0.046446020912223177 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7793103448275862, "acc_stderr": 0.03455930201924814, "acc_norm": 0.7793103448275862, "acc_norm_stderr": 0.03455930201924814 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.6666666666666666, "acc_stderr": 0.024278568024307706, "acc_norm": 0.6666666666666666, "acc_norm_stderr": 0.024278568024307706 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.5793650793650794, "acc_stderr": 0.04415438226743745, "acc_norm": 0.5793650793650794, "acc_norm_stderr": 0.04415438226743745 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.51, "acc_stderr": 0.05024183937956912, "acc_norm": 0.51, "acc_norm_stderr": 0.05024183937956912 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.8806451612903226, "acc_stderr": 0.018443411325315396, "acc_norm": 0.8806451612903226, "acc_norm_stderr": 0.018443411325315396 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.6206896551724138, "acc_stderr": 0.034139638059062345, "acc_norm": 0.6206896551724138, "acc_norm_stderr": 0.034139638059062345 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.82, "acc_stderr": 0.03861229196653694, "acc_norm": 0.82, "acc_norm_stderr": 0.03861229196653694 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.8666666666666667, "acc_stderr": 0.026544435312706467, "acc_norm": 0.8666666666666667, "acc_norm_stderr": 0.026544435312706467 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.9090909090909091, "acc_stderr": 0.02048208677542421, "acc_norm": 0.9090909090909091, "acc_norm_stderr": 0.02048208677542421 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9792746113989638, "acc_stderr": 0.010281417011909039, "acc_norm": 0.9792746113989638, "acc_norm_stderr": 0.010281417011909039 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.8, "acc_stderr": 0.020280805062535726, "acc_norm": 0.8, "acc_norm_stderr": 0.020280805062535726 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3592592592592593, "acc_stderr": 0.029252905927251972, "acc_norm": 0.3592592592592593, "acc_norm_stderr": 0.029252905927251972 }, "harness|hendrycksTest-high_school_microeconomics|5": { "acc": 0.840336
