open-llm-leaderboard-old/details_yihan6324__llama2-13b-instructmining-40k-sharegpt
收藏数据集概述
数据集摘要
该数据集是在评估模型 yihan6324/llama2-13b-instructmining-40k-sharegpt 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 该数据集包含 61 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，每个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_yihan6324__llama2-13b-instructmining-40k-sharegpt", "harness_truthfulqa_mc_0", split="train")
最新结果
以下是 2023-08-17T15:06:33.773565 运行的最新结果：
python { "all": { "acc": 0.5659221179678169, "acc_stderr": 0.03435610194042996, "acc_norm": 0.5698526105353496, "acc_norm_stderr": 0.03433517528186645, "mc1": 0.35862913096695226, "mc1_stderr": 0.016789289499502022, "mc2": 0.5244082340441981, "mc2_stderr": 0.015623466277080963 }, "harness|arc:challenge|25": { "acc": 0.5656996587030717, "acc_stderr": 0.01448470304885736, "acc_norm": 0.5998293515358362, "acc_norm_stderr": 0.014317197787809169 }, "harness|hellaswag|10": { "acc": 0.6328420633339972, "acc_stderr": 0.004810449343572395, "acc_norm": 0.8306114319856602, "acc_norm_stderr": 0.003743281749373634 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.35, "acc_stderr": 0.0479372485441102, "acc_norm": 0.35, "acc_norm_stderr": 0.0479372485441102 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.48148148148148145, "acc_stderr": 0.043163785995113245, "acc_norm": 0.48148148148148145, "acc_norm_stderr": 0.043163785995113245 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.625, "acc_stderr": 0.039397364351956274, "acc_norm": 0.625, "acc_norm_stderr": 0.039397364351956274 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.59, "acc_stderr": 0.049431107042371025, "acc_norm": 0.59, "acc_norm_stderr": 0.049431107042371025 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.6150943396226415, "acc_stderr": 0.02994649856769995, "acc_norm": 0.6150943396226415, "acc_norm_stderr": 0.02994649856769995 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.6111111111111112, "acc_stderr": 0.04076663253918567, "acc_norm": 0.6111111111111112, "acc_norm_stderr": 0.04076663253918567 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.41, "acc_stderr": 0.04943110704237102, "acc_norm": 0.41, "acc_norm_stderr": 0.04943110704237102 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.37, "acc_stderr": 0.048523658709391, "acc_norm": 0.37, "acc_norm_stderr": 0.048523658709391 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.5895953757225434, "acc_stderr": 0.03750757044895537, "acc_norm": 0.5895953757225434, "acc_norm_stderr": 0.03750757044895537 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.3431372549019608, "acc_stderr": 0.04724007352383887, "acc_norm": 0.3431372549019608, "acc_norm_stderr": 0.04724007352383887 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.4595744680851064, "acc_stderr": 0.03257901482099835, "acc_norm": 0.4595744680851064, "acc_norm_stderr": 0.03257901482099835 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.23684210526315788, "acc_stderr": 0.039994238792813344, "acc_norm": 0.23684210526315788, "acc_norm_stderr": 0.039994238792813344 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.503448275862069, "acc_stderr": 0.04166567577101579, "acc_norm": 0.503448275862069, "acc_norm_stderr": 0.04166567577101579 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.29365079365079366, "acc_stderr": 0.023456037383982026, "acc_norm": 0.29365079365079366, "acc_norm_stderr": 0.023456037383982026 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.36507936507936506, "acc_stderr": 0.04306241259127153, "acc_norm": 0.36507936507936506, "acc_norm_stderr": 0.04306241259127153 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.35, "acc_stderr": 0.047937248544110196, "acc_norm": 0.35, "acc_norm_stderr": 0.047937248544110196 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.6709677419354839, "acc_stderr": 0.026729499068349958, "acc_norm": 0.6709677419354839, "acc_norm_stderr": 0.026729499068349958 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.45320197044334976, "acc_stderr": 0.03502544650845872, "acc_norm": 0.45320197044334976, "acc_norm_stderr": 0.03502544650845872 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.56, "acc_stderr": 0.049888765156985884, "acc_norm": 0.56, "acc_norm_stderr": 0.049888765156985884 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.6787878787878788, "acc_stderr": 0.0364620496325381, "acc_norm": 0.6787878787878788, "acc_norm_stderr": 0.0364620496325381 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.7171717171717171, "acc_stderr": 0.03208779558786753, "acc_norm": 0.7171717171717171, "acc_norm_stderr": 0.03208779558786753 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.8134715025906736, "acc_stderr": 0.02811209121011748, "acc_norm": 0.8134715025906736, "acc_norm_stderr": 0.02811209121011748 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.5333333333333333, "acc_stderr": 0.025294608023986472, "acc_norm": 0.5333333333333333, "acc_norm_stderr": 0.025294608023986472 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.26666666666666666, "acc_stderr": 0.026962424325073838, "acc_norm": 0
