open-llm-leaderboard/details_quantumaikr__quantumairk-llama-2-70B-instruct

该数据集是在评估模型quantumaikr/quantumairk-llama-2-70B-instruct时自动创建的，主要用于在Open LLM Leaderboard上进行评估。数据集包含61个配置，每个配置对应一个评估任务。数据集由1次运行生成，每次运行的结果作为一个特定的分割存储，分割名称使用运行的时间戳。train分割始终指向最新的结果。此外，还有一个名为results的配置，存储了所有运行的聚合结果，用于在Open LLM Leaderboard上计算和显示聚合指标。This dataset was automatically generated during the evaluation of the model quantumaikr/quantumairk-llama-2-70B-instruct, and is primarily intended for evaluation on the Open LLM Leaderboard. It contains 61 configurations, each corresponding to one evaluation task. The dataset is created via a single run, with the results of each run stored as a specific data split, where the split name uses the timestamp of the corresponding run. The "train" split always points to the most recent results. Additionally, there is a configuration named "results" that stores the aggregated results across all runs, which is used to calculate and display aggregate metrics on the Open LLM Leaderboard.

原始信息汇总

数据集概述

数据集摘要

该数据集是在对模型 quantumaikr/quantumairk-llama-2-70B-instruct 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 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_quantumaikr__quantumairk-llama-2-70B-instruct", "harness_truthfulqa_mc_0", split="train")

最新结果

以下是 最新结果来自 run 2023-09-03T17:56:31.707465 的摘要：

python { "all": { "acc": 0.7034684893089378, "acc_stderr": 0.03095672218595075, "acc_norm": 0.7074134061674743, "acc_norm_stderr": 0.03092655497572306, "mc1": 0.3818849449204406, "mc1_stderr": 0.017008101939163495, "mc2": 0.5442099278190564, "mc2_stderr": 0.014507128903598229 }, ... }

配置详情

• config_name: harness_arc_challenge_25

  • split: 2023_09_03T17_56_31.707465
    • path: **/details_harness|arc:challenge|25_2023-09-03T17:56:31.707465.parquet
  • split: latest
    • path: **/details_harness|arc:challenge|25_2023-09-03T17:56:31.707465.parquet

• config_name: harness_hellaswag_10

  • split: 2023_09_03T17_56_31.707465
    • path: **/details_harness|hellaswag|10_2023-09-03T17:56:31.707465.parquet
  • split: latest
    • path: **/details_harness|hellaswag|10_2023-09-03T17:56:31.707465.parquet

• config_name: harness_hendrycksTest_5

  • split: 2023_09_03T17_56_31.707465
    • path:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T17:56:31.707465.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-09-03T17:56:31.707465.parquet
      • ...
  • split: latest
    • path:
      • **/details_harness|hendrycksTest-abstract_algebra|5_2023-09-03T17:56:31.707465.parquet
      • **/details_harness|hendrycksTest-anatomy|5_2023-09-03T17:56:31.707465.parquet
      • ...