open-llm-leaderboard-old/details_bigscience__bloomz-560m

Name: open-llm-leaderboard-old/details_bigscience__bloomz-560m
Creator: open-llm-leaderboard-old
Published: 2023-12-04 12:37:21
License: 暂无描述

Hugging Face2023-12-04 更新2024-06-22 收录

下载链接：

https://hf-mirror.com/datasets/open-llm-leaderboard-old/details_bigscience__bloomz-560m

下载链接

链接失效反馈

官方服务：

资源简介：

--- pretty_name: Evaluation run of bigscience/bloomz-560m dataset_summary: "Dataset automatically created during the evaluation run of model\ \ [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on the\ \ [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\ \nThe dataset is composed of 3 configuration, each one coresponding to one of the\ \ evaluated task.\n\nThe dataset has been created from 8 run(s). Each run can be\ \ found as a specific split in each configuration, the split being named using the\ \ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\ \nAn additional configuration \"results\" store all the aggregated results of the\ \ run (and is used to compute and display the aggregated metrics on the [Open LLM\ \ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\ \nTo load the details from a run, you can for instance do the following:\n```python\n\ from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_bigscience__bloomz-560m\"\ ,\n\t\"harness_gsm8k_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\nThese\ \ are the [latest results from run 2023-12-04T12:37:15.813527](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloomz-560m/blob/main/results_2023-12-04T12-37-15.813527.json)(note\ \ that their might be results for other tasks in the repos if successive evals didn't\ \ cover the same tasks. You find each in the results and the \"latest\" split for\ \ each eval):\n\n```python\n{\n \"all\": {\n \"acc\": 0.0,\n \"\ acc_stderr\": 0.0\n },\n \"harness|gsm8k|5\": {\n \"acc\": 0.0,\n \ \ \"acc_stderr\": 0.0\n }\n}\n```" repo_url: https://huggingface.co/bigscience/bloomz-560m leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard point_of_contact: clementine@hf.co configs: - config_name: harness_drop_3 data_files: - split: 2023_10_13T02_59_38.387630 path: - '**/details_harness|drop|3_2023-10-13T02-59-38.387630.parquet' - split: latest path: - '**/details_harness|drop|3_2023-10-13T02-59-38.387630.parquet' - config_name: harness_gsm8k_5 data_files: - split: 2023_10_13T02_59_38.387630 path: - '**/details_harness|gsm8k|5_2023-10-13T02-59-38.387630.parquet' - split: 2023_12_03T14_34_05.520160 path: - '**/details_harness|gsm8k|5_2023-12-03T14-34-05.520160.parquet' - split: 2023_12_03T14_34_17.552843 path: - '**/details_harness|gsm8k|5_2023-12-03T14-34-17.552843.parquet' - split: 2023_12_03T15_36_24.223775 path: - '**/details_harness|gsm8k|5_2023-12-03T15-36-24.223775.parquet' - split: 2023_12_03T15_36_26.532570 path: - '**/details_harness|gsm8k|5_2023-12-03T15-36-26.532570.parquet' - split: 2023_12_04T09_27_25.322225 path: - '**/details_harness|gsm8k|5_2023-12-04T09-27-25.322225.parquet' - split: 2023_12_04T12_37_10.556639 path: - '**/details_harness|gsm8k|5_2023-12-04T12-37-10.556639.parquet' - split: 2023_12_04T12_37_15.813527 path: - '**/details_harness|gsm8k|5_2023-12-04T12-37-15.813527.parquet' - split: latest path: - '**/details_harness|gsm8k|5_2023-12-04T12-37-15.813527.parquet' - config_name: harness_winogrande_5 data_files: - split: 2023_10_13T02_59_38.387630 path: - '**/details_harness|winogrande|5_2023-10-13T02-59-38.387630.parquet' - split: latest path: - '**/details_harness|winogrande|5_2023-10-13T02-59-38.387630.parquet' - config_name: results data_files: - split: 2023_10_13T02_59_38.387630 path: - results_2023-10-13T02-59-38.387630.parquet - split: 2023_12_03T14_34_05.520160 path: - results_2023-12-03T14-34-05.520160.parquet - split: 2023_12_03T14_34_17.552843 path: - results_2023-12-03T14-34-17.552843.parquet - split: 2023_12_03T15_36_24.223775 path: - results_2023-12-03T15-36-24.223775.parquet - split: 2023_12_03T15_36_26.532570 path: - results_2023-12-03T15-36-26.532570.parquet - split: 2023_12_04T09_27_25.322225 path: - results_2023-12-04T09-27-25.322225.parquet - split: 2023_12_04T12_37_10.556639 path: - results_2023-12-04T12-37-10.556639.parquet - split: 2023_12_04T12_37_15.813527 path: - results_2023-12-04T12-37-15.813527.parquet - split: latest path: - results_2023-12-04T12-37-15.813527.parquet --- # Dataset Card for Evaluation run of bigscience/bloomz-560m ## Dataset Description - **Homepage:** - **Repository:** https://huggingface.co/bigscience/bloomz-560m - **Paper:** - **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard - **Point of Contact:** clementine@hf.co ### Dataset Summary Dataset automatically created during the evaluation run of model [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). The dataset is composed of 3 configuration, each one coresponding to one of the evaluated task. The dataset has been created from 8 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results. An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)). To load the details from a run, you can for instance do the following: ```python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bigscience__bloomz-560m", "harness_gsm8k_5", split="train") ``` ## Latest results These are the [latest results from run 2023-12-04T12:37:15.813527](https://huggingface.co/datasets/open-llm-leaderboard/details_bigscience__bloomz-560m/blob/main/results_2023-12-04T12-37-15.813527.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval): ```python { "all": { "acc": 0.0, "acc_stderr": 0.0 }, "harness|gsm8k|5": { "acc": 0.0, "acc_stderr": 0.0 } } ``` ### Supported Tasks and Leaderboards [More Information Needed] ### Languages [More Information Needed] ## Dataset Structure ### Data Instances [More Information Needed] ### Data Fields [More Information Needed] ### Data Splits [More Information Needed] ## Dataset Creation ### Curation Rationale [More Information Needed] ### Source Data #### Initial Data Collection and Normalization [More Information Needed] #### Who are the source language producers? [More Information Needed] ### Annotations #### Annotation process [More Information Needed] #### Who are the annotators? [More Information Needed] ### Personal and Sensitive Information [More Information Needed] ## Considerations for Using the Data ### Social Impact of Dataset [More Information Needed] ### Discussion of Biases [More Information Needed] ### Other Known Limitations [More Information Needed] ## Additional Information ### Dataset Curators [More Information Needed] ### Licensing Information [More Information Needed] ### Citation Information [More Information Needed] ### Contributions [More Information Needed]

提供机构：

open-llm-leaderboard-old

原始信息汇总

数据集卡片 for Evaluation run of bigscience/bloomz-560m

数据集描述

数据集摘要

数据集是在模型 bigscience/bloomz-560m 在 Open LLM Leaderboard 上的评估运行期间自动创建的。

数据集由3个配置组成，每个配置对应一个评估任务。

数据集从8次运行中创建。每次运行可以在每个配置中找到一个特定的分割，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（用于计算并在 Open LLM Leaderboard 上显示聚合指标）。

要加载某个运行的详细信息，可以执行以下操作： python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_bigscience__bloomz-560m", "harness_gsm8k_5", split="train")

open-llm-leaderboard-old/details_bigscience__bloomz-560m

数据集卡片 for Evaluation run of bigscience/bloomz-560m

数据集描述

数据集摘要

最新结果

配置