|
--- |
|
license: apache-2.0 |
|
base_model: google-t5/t5-small |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
datasets: |
|
- govreport-summarization |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-small-finetuned-govReport-3072 |
|
results: |
|
- task: |
|
name: Sequence-to-sequence Language Modeling |
|
type: text2text-generation |
|
dataset: |
|
name: govreport-summarization |
|
type: govreport-summarization |
|
config: document |
|
split: validation |
|
args: document |
|
metrics: |
|
- name: Rouge1 |
|
type: rouge |
|
value: 0.0371 |
|
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-govReport-3072 |
|
|
|
This model is a fine-tuned version of [google-t5/t5-small](https://huggingface.co/google-t5/t5-small) on the govreport-summarization dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.8367 |
|
- Rouge1: 0.0371 |
|
- Rouge2: 0.0142 |
|
- Rougel: 0.0316 |
|
- Rougelsum: 0.0352 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 19.9287 | 0.99 | 31 | 11.5775 | 0.0331 | 0.0151 | 0.0293 | 0.0317 | |
|
| 12.489 | 1.98 | 62 | 9.1322 | 0.0373 | 0.0162 | 0.0322 | 0.0351 | |
|
| 10.8693 | 2.98 | 93 | 7.8834 | 0.0367 | 0.0153 | 0.0327 | 0.0348 | |
|
| 9.1603 | 4.0 | 125 | 6.8580 | 0.0374 | 0.0162 | 0.0322 | 0.0355 | |
|
| 8.2587 | 4.99 | 156 | 5.7038 | 0.0382 | 0.0154 | 0.0326 | 0.0366 | |
|
| 6.6869 | 5.98 | 187 | 4.8553 | 0.0388 | 0.0159 | 0.0341 | 0.037 | |
|
| 5.8997 | 6.98 | 218 | 4.3049 | 0.0383 | 0.0145 | 0.0336 | 0.036 | |
|
| 5.0285 | 8.0 | 250 | 3.9143 | 0.0369 | 0.0138 | 0.0311 | 0.035 | |
|
| 4.5944 | 8.99 | 281 | 3.8533 | 0.0376 | 0.0149 | 0.032 | 0.0353 | |
|
| 4.5239 | 9.92 | 310 | 3.8367 | 0.0371 | 0.0142 | 0.0316 | 0.0352 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.17.0 |
|
- Tokenizers 0.15.1 |
