BART-Base Finance News Summarization is designed to quickly condense finance news articles into shorter summaries, capturing key financial data and market trends. This model helps financial analysts, investors, and journalists rapidly gather insights from extensive news coverage.

Intended uses & limitations

This model is tailored for summarizing financial news content. It is not intended for non-finance news or for use in generating original news content. Users should be aware of potential biases in the training data that might affect the neutrality of the summaries.

Training and evaluation data

The model was trained on a dataset composed of thousands of finance-related news articles, each paired with professionally written summaries to ensure high-quality training.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9, 0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3.0

Framework versions

Transformers 4.38.2
Pytorch 2.2.1+cu121
Tokenizers 0.15.2

yatharth97/bart-base-news-summarization

bart-base-finance-news-summarization

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Framework versions

yatharth97/
bart-base-news-summarization