| | --- |
| | license: apache-2.0 |
| | tags: |
| | - generated_from_trainer |
| | model-index: |
| | - name: mt5-large-bn_sum_total_data |
| | results: [] |
| | --- |
| | |
| | <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| | should probably proofread and complete it, then remove this comment. --> |
| |
|
| | # mt5-large-bn_sum_total_data |
| | |
| | This model is a fine-tuned version of [google/mt5-large](https://huggingface.co/google/mt5-large) on [this](https://www.kaggle.com/datasets/hasanmoni/bengali-text-summarization) dataset. |
| | |
| | ## Model description |
| | |
| | Our fine-tuned MT5-large model has significantly outperformed the state-of-the-art model (CSEBUETNLP/mT5_multilingual_XLSum) for Bangla text summarization. We achieved a ROUGE score of approximately 43, surpassing the previous record of 29.5653. This improvement demonstrates the effectiveness of our approach and highlights the potential for further advancements in Bangla NLP. |
| | ## Intended uses & limitations |
| | |
| | Has a limitation for banglish texts |
| | |
| | ## Training and evaluation data |
| | |
| | [Dataset](https://www.kaggle.com/datasets/hasanmoni/bengali-text-summarization) |
| | |
| | ## Training procedure |
| | |
| | ### Training hyperparameters |
| | |
| | The following hyperparameters were used during training: |
| | - learning_rate: 5.6e-05 |
| | - train_batch_size: 6 |
| | - eval_batch_size: 6 |
| | - seed: 42 |
| | - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| | - lr_scheduler_type: linear |
| | - num_epochs: 10 |
| | |
| | ### Framework versions |
| | |
| | - Transformers 4.27.1 |
| | - Pytorch 1.13.1+cu116 |
| | - Datasets 2.10.1 |
| | - Tokenizers 0.13.2 |
| | |
