open-llm-leaderboard/details_WizardLM__WizardCoder-Python-34B-V1.0
收藏Hugging Face2023-09-30 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/open-llm-leaderboard/details_WizardLM__WizardCoder-Python-34B-V1.0
下载链接
链接失效反馈官方服务:
资源简介:
该数据集是在评估模型WizardLM/WizardCoder-Python-34B-V1.0时自动创建的,数据集由64个配置组成,每个配置对应一个评估任务。数据集由3次运行生成,每次运行的结果作为特定分割存储在配置中,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。
提供机构:
open-llm-leaderboard
原始信息汇总
数据集概述
数据集名称
- Evaluation run of WizardLM/WizardCoder-Python-34B-V1.0
数据集描述
- 该数据集是在评估模型 WizardLM/WizardCoder-Python-34B-V1.0 在 Open LLM Leaderboard 上的自动创建的。
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。
- 数据集从 3 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。
- 额外的配置 "results" 存储所有运行的聚合结果,用于计算和显示在 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_WizardLM__WizardCoder-Python-34B-V1.0", "harness_winogrande_5", split="train")
最新结果
- 这些是最新结果,来自 2023-09-30T13:26:26.501307 的运行: python { "all": { "em": 0.19379194630872484, "em_stderr": 0.004047912159759954, "f1": 0.2506229026845643, "f1_stderr": 0.0041031622757888245, "acc": 0.38913655258910956, "acc_stderr": 0.010569829944033455 }, "harness|drop|3": { "em": 0.19379194630872484, "em_stderr": 0.004047912159759954, "f1": 0.2506229026845643, "f1_stderr": 0.0041031622757888245 }, "harness|gsm8k|5": { "acc": 0.09476876421531463, "acc_stderr": 0.008067791560015424 }, "harness|winogrande|5": { "acc": 0.6835043409629045, "acc_stderr": 0.013071868328051487 } }
配置详情
-
harness_arc_challenge_25
- 分割:2023_08_28T14_24_48.520314
- 路径:
**/details_harness|arc:challenge|25_2023-08-28T14:24:48.520314.parquet
- 路径:
- 分割:2023_08_30T15_50_41.710615
- 路径:
**/details_harness|arc:challenge|25_2023-08-30T15:50:41.710615.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|arc:challenge|25_2023-08-30T15:50:41.710615.parquet
- 路径:
- 分割:2023_08_28T14_24_48.520314
-
harness_drop_3
- 分割:2023_09_30T13_26_26.501307
- 路径:
**/details_harness|drop|3_2023-09-30T13-26-26.501307.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|drop|3_2023-09-30T13-26-26.501307.parquet
- 路径:
- 分割:2023_09_30T13_26_26.501307
-
harness_gsm8k_5
- 分割:2023_09_30T13_26_26.501307
- 路径:
**/details_harness|gsm8k|5_2023-09-30T13-26-26.501307.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|gsm8k|5_2023-09-30T13-26-26.501307.parquet
- 路径:
- 分割:2023_09_30T13_26_26.501307
-
harness_hellaswag_10
- 分割:2023_08_28T14_24_48.520314
- 路径:
**/details_harness|hellaswag|10_2023-08-28T14:24:48.520314.parquet
- 路径:
- 分割:2023_08_30T15_50_41.710615
- 路径:
**/details_harness|hellaswag|10_2023-08-30T15:50:41.710615.parquet
- 路径:
- 分割:latest
- 路径:
**/details_harness|hellaswag|10_2023-08-30T15:50:41.710615.parquet
- 路径:
- 分割:2023_08_28T14_24_48.520314
-
harness_hendrycksTest_5
- 分割:2023_08_28T14_24_48.520314
- 路径:
**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-anatomy|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-astronomy|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-business_ethics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-college_biology|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-college_chemistry|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-college_computer_science|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-college_mathematics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-college_medicine|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-college_physics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-computer_security|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-econometrics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-formal_logic|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-global_facts|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_biology|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_geography|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_physics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-human_aging|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-human_sexuality|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-international_law|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-jurisprudence|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-machine_learning|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-management|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-marketing|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-medical_genetics|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-miscellaneous|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-moral_disputes|5_2023-08-28T14:24:48.520314.parquet - 路径:
**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-28T14:24:48.520314.parquet - 路径:`**/details_
- 路径:
- 分割:2023_08_28T14_24_48.520314



