Downloads · 30 days
0
mia-project-2025/T5-base-adapter-financial-news-articles
T5-base-adapter-financial-news-articles is a machine learning model from mia-project-2025. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This repository contains a T5-base model fine-tuned using AdaLoRA (Adaptive Low-Rank Adaptation) on the Financial News Articles Dataset to generate concise titles from financial news articles.
Downloads · 30 days
0
Access
Public
Updated Aug 24, 2025
Repo size
17.3 MB
Likes
0
Public
Click a slice to open those files.
.pt11 MB · 48%
From the Hugging Face model README
This repository contains a T5-base model fine-tuned using AdaLoRA (Adaptive Low-Rank Adaptation) on the Financial News Articles Dataset to generate concise titles from financial news articles.
mrm8488/t5-base-finetuned-summarize-newsashraq/financial-news-articles (80/20 train/test split)init_r): 6lora_alpha): 64q, v (query and value projections in attention)lora_dropout): 0.05Only AdaLoRA parameters are trained; the base T5 parameters remain frozen. The rank is adapted dynamically during training.
| Metric | Score |
|---|---|
| ROUGE-1 | 65.66 |
| ROUGE-2 | 51.72 |
| ROUGE-L | 63.73 |
| ROUGE-Lsum | 63.73 |
These results were obtained after 15 epochs of AdaLoRA fine-tuning on 4 GPUs.