open-llm-leaderboard-old/details_togethercomputer__RedPajama-INCITE-Chat-3B-v1

该数据集是在模型 togethercomputer/RedPajama-INCITE-Chat-3B-v1 在 Open LLM Leaderboard 上的评估过程中自动生成的。数据集包含 64 个配置，每个配置对应一个被评估的任务。它由 2 次运行生成，每次运行在每个配置中表示为一个特定的分割。train 分割始终指向最新的结果。一个名为 results 的额外配置存储了所有运行的聚合结果，这些结果用于计算和显示 Open LLM Leaderboard 上的聚合指标。README 还提供了一个如何使用 Python 中的 datasets 库加载运行细节的示例。

原始信息汇总

数据集概述

该数据集是在评估模型 togethercomputer/RedPajama-INCITE-Chat-3B-v1 的过程中自动创建的，用于 Open LLM Leaderboard。

数据集组成

• 数据集包含 64 个配置，每个配置对应一个评估任务。
• 数据集由 2 次运行创建，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。
• 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_togethercomputer__RedPajama-INCITE-Chat-3B-v1", "harness_winogrande_5", split="train")

最新结果

以下是 2023-10-17T17:32:08.397205 运行的最新结果：

python { "all": { "em": 0.0037751677852348995, "em_stderr": 0.0006280387809484473, "f1": 0.06162122483221491, "f1_stderr": 0.00147164825377704, "acc": 0.3301989081920304, "acc_stderr": 0.007680342762990863 }, "harness|drop|3": { "em": 0.0037751677852348995, "em_stderr": 0.0006280387809484473, "f1": 0.06162122483221491, "f1_stderr": 0.00147164825377704 }, "harness|gsm8k|5": { "acc": 0.00530705079605762, "acc_stderr": 0.002001305720948034 }, "harness|winogrande|5": { "acc": 0.6550907655880032, "acc_stderr": 0.013359379805033692 } }

配置详情

• harness_arc_challenge_25

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|arc:challenge|25_2023-07-19T15:21:48.380977.parquet

• harness_drop_3

  • 分割: 2023_10_17T17_32_08.397205, latest
  • 路径: **/details_harness|drop|3_2023-10-17T17-32-08.397205.parquet

• harness_gsm8k_5

  • 分割: 2023_10_17T17_32_08.397205, latest
  • 路径: **/details_harness|gsm8k|5_2023-10-17T17-32-08.397205.parquet

• harness_hellaswag_10

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hellaswag|10_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: 多个路径，例如 **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_abstract_algebra_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_anatomy_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-anatomy|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_astronomy_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-astronomy|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_business_ethics_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-business_ethics|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_clinical_knowledge_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_college_biology_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-college_biology|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_college_chemistry_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_college_computer_science_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_college_mathematics_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_college_medicine_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-college_medicine|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_college_physics_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-college_physics|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_computer_security_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-computer_security|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_conceptual_physics_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_econometrics_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-econometrics|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_electrical_engineering_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T15:21:48.380977.parquet

• harness_hendrycksTest_elementary_mathematics_5

  • 分割: 2023_07_19T15_21_48.380977, latest
  • 路径: **/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T15:21:48.380977.parquet