|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-BBCNews |
|
results: [] |
|
language: |
|
- en |
|
pipeline_tag: summarization |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# t5-small-finetuned-BBCNews |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the BBC News Articles dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7321 |
|
- Rouge1: 0.1672 |
|
- Rouge2: 0.1387 |
|
- Rougel: 0.1605 |
|
- Rougelsum: 0.1622 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5.6e-05 |
|
- train_batch_size: 5 |
|
- eval_batch_size: 5 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 1.0538 | 1.0 | 344 | 0.7877 | 0.156 | 0.1219 | 0.1472 | 0.1492 | |
|
| 0.7611 | 2.0 | 688 | 0.7479 | 0.1641 | 0.1333 | 0.1565 | 0.1577 | |
|
| 0.7189 | 3.0 | 1032 | 0.7400 | 0.1659 | 0.1365 | 0.1589 | 0.1606 | |
|
| 0.7021 | 4.0 | 1376 | 0.7370 | 0.1671 | 0.138 | 0.1603 | 0.1618 | |
|
| 0.6976 | 5.0 | 1720 | 0.7321 | 0.1672 | 0.1387 | 0.1605 | 0.1622 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
