open-llm-leaderboard-old/details_AA051610__A0121

数据集是在模型AA051610/A0121的评估运行期间自动创建的，用于Open LLM Leaderboard。数据集由63个配置组成，每个配置对应一个评估任务。数据集由1次运行生成，每次运行可以在每个配置中找到，运行的时间戳作为分割名称。"train"分割始终指向最新结果。此外，"results"配置存储了所有运行的聚合结果，并用于计算和显示Open LLM Leaderboard上的聚合指标。

原始信息汇总

数据集概述

该数据集是在模型 AA051610/A0121 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集包含 63 个配置，每个配置对应一个评估任务。数据集从 1 次运行中创建，每个运行可以在每个配置中找到一个特定的拆分，拆分名称使用运行的时间戳。"train" 拆分始终指向最新的结果。

数据集结构

数据集包含以下配置：

• harness_arc_challenge_25

  • 拆分：2024_01_21T06_38_55.912986
  • 路径：**/details_harness|arc:challenge|25_2024-01-21T06-38-55.912986.parquet
  • 拆分：latest
  • 路径：**/details_harness|arc:challenge|25_2024-01-21T06-38-55.912986.parquet

• harness_gsm8k_5

  • 拆分：2024_01_21T06_38_55.912986
  • 路径：**/details_harness|gsm8k|5_2024-01-21T06-38-55.912986.parquet
  • 拆分：latest
  • 路径：**/details_harness|gsm8k|5_2024-01-21T06-38-55.912986.parquet

• harness_hellaswag_10

  • 拆分：2024_01_21T06_38_55.912986
  • 路径：**/details_harness|hellaswag|10_2024-01-21T06-38-55.912986.parquet
  • 拆分：latest
  • 路径：**/details_harness|hellaswag|10_2024-01-21T06-38-55.912986.parquet

• harness_hendrycksTest_5

  • 拆分：2024_01_21T06_38_55.912986
  • 路径：
    • **/details_harness|hendrycksTest-abstract_algebra|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-anatomy|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-astronomy|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-business_ethics|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-clinical_knowledge|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-college_biology|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-college_chemistry|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-college_computer_science|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-college_mathematics|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-college_medicine|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-college_physics|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-computer_security|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-conceptual_physics|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-econometrics|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-electrical_engineering|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-elementary_mathematics|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-formal_logic|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-global_facts|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-high_school_biology|5_2024-01-21T06-38-55.912986.parquet
    • **/details_harness|hendrycksTest-high_school_chemistry|5_2024-01-21T06-38-55.912986.parquet

最新结果

以下是 2024-01-21T06:38:55.912986 运行 的最新结果：

python { "all": { "acc": 0.7447539059303026, "acc_stderr": 0.028988249523275268, "acc_norm": 0.7497779847824153, "acc_norm_stderr": 0.029529280939468258, "mc1": 0.40514075887392903, "mc1_stderr": 0.01718561172775337, "mc2": 0.5961151164765033, "mc2_stderr": 0.01535344953348685 }, "harness|arc:challenge|25": { "acc": 0.6467576791808873, "acc_stderr": 0.013967822714840056, "acc_norm": 0.6715017064846417, "acc_norm_stderr": 0.0137249784655373 }, "harness|hellaswag|10": { "acc": 0.6623182632941645, "acc_stderr": 0.004719529099913134, "acc_norm": 0.854511053574985, "acc_norm_stderr": 0.00351872525736559 }, "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": 0.7555555555555555, "acc_stderr": 0.03712537833614866, "acc_norm": 0.7555555555555555, "acc_norm_stderr": 0.03712537833614866 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.868421052631579, "acc_stderr": 0.027508689533549912, "acc_norm": 0.868421052631579, "acc_norm_stderr": 0.027508689533549912 }, "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": 0.7924528301886793, "acc_stderr": 0.02495991802891127, "acc_norm": 0.7924528301886793, "acc_norm_stderr": 0.02495991802891127 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.8263888888888888, "acc_stderr": 0.03167473383795718, "acc_norm": 0.8263888888888888, "acc_norm_stderr": 0.03167473383795718 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.44, "acc_stderr": 0.04988876515698589, "acc_norm": 0.44, "acc_norm_stderr": 0.04988876515698589 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.6, "acc_stderr": 0.04923659639173309, "acc_norm": 0.6, "acc_norm_stderr": 0.04923659639173309 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.43, "acc_stderr": 0.049756985195624284, "acc_norm": 0.43, "acc_norm_stderr": 0.049756985195624284 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6994219653179191, "acc_stderr": 0.03496101481191178, "acc_norm": 0.6994219653179191, "acc_norm_stderr": 0.03496101481191178 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.5294117647058824, "acc_stderr": 0.049665709039785295, "acc_norm": 0.5294117647058824, "acc_norm_stderr": 0.049665709039785295 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.77, "acc_stderr": 0.04229525846816505, "acc_norm": 0.77, "acc_norm_stderr": 0.04229525846816505 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.7574468085106383, "acc_stderr": 0.02802022627120022, "acc_norm": 0.7574468085106383, "acc_norm_stderr": 0.02802022627120022 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.6403508771929824, "acc_stderr": 0.04514496132873633, "acc_norm": 0.6403508771929824, "acc_norm_stderr": 0.04514496132873633 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.7448275862068966, "acc_stderr": 0.03632984052707842, "acc_norm": 0.7448275862068966, "acc_norm_stderr": 0.036329