five

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

收藏
Hugging Face2023-10-17 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_togethercomputer__RedPajama-INCITE-Chat-3B-v1
下载链接
链接失效反馈
官方服务:
资源简介:
该数据集是在模型 togethercomputer/RedPajama-INCITE-Chat-3B-v1 在 Open LLM Leaderboard 上的评估运行期间自动创建的。数据集由 64 个配置组成,每个配置对应一个被评估的任务。数据集是从 2 次运行中生成的,每次运行在每个配置中表示为特定的分割,分割名称由运行的时间戳命名。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 还提供了如何使用 `datasets` 库中的 `load_dataset` 函数加载数据集的示例。

This dataset was automatically created during the evaluation run of the model togethercomputer/RedPajama-INCITE-Chat-3B-v1 on the Open LLM Leaderboard. The dataset consists of 64 configurations, each corresponding to one evaluated task. The dataset is generated from 2 runs, where each run is represented as a specific split under each configuration, and the split name is named after the timestamp of the corresponding run. The 'train' split always points to the most recent results. An additional configuration named 'results' stores the aggregated results across all runs, which are used to calculate and display the aggregated metrics on the Open LLM Leaderboard. The README also provides examples of how to load the dataset using the `load_dataset` function from the `datasets` library.
提供机构:
open-llm-leaderboard
原始信息汇总

数据集概述

该数据集是在对模型 togethercomputer/RedPajama-INCITE-Chat-3B-v1 进行评估运行期间自动创建的。数据集包含64个配置,每个配置对应一个评估任务。数据集从2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。

数据集结构

数据集包含以下配置:

  • harness_arc_challenge_25

    • 分割:2023_07_19T15_21_48.380977
    • 路径:**/details_harness|arc:challenge|25_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|drop|3_2023-10-17T17-32-08.397205.parquet
    • 分割: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
    • 路径:**/details_harness|gsm8k|5_2023-10-17T17-32-08.397205.parquet
    • 分割: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
    • 路径:**/details_harness|hellaswag|10_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:多个文件路径
    • 分割:latest
    • 路径:多个文件路径
  • harness_hendrycksTest_abstract_algebra_5

    • 分割:2023_07_19T15_21_48.380977
    • 路径:**/details_harness|hendrycksTest-abstract_algebra|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-anatomy|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-astronomy|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-business_ethics|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-clinical_knowledge|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-college_biology|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-college_chemistry|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-college_computer_science|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-college_mathematics|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-college_medicine|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-college_physics|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-computer_security|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-conceptual_physics|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-econometrics|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-electrical_engineering|5_2023-07-19T15:21:48.380977.parquet
    • 分割: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
    • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T15:21:48.380977.parquet
    • 分割:latest
    • 路径:**/details_harness|hendrycksTest-elementary_mathematics|5_2023-07-19T15:21:48.380977.parquet

最新结果

以下是2023年10月17日17:32:08.397205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 } }

二维码
社区交流群
二维码
科研交流群
商业服务