|
--- |
|
license: apache-2.0 |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-base-news_headlines |
|
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. --> |
|
|
|
# t5-base-news_headlines |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.8974 |
|
- Rouge1: 57.2262 |
|
- Rouge2: 42.0378 |
|
- Rougel: 56.5748 |
|
- Rougelsum: 56.5201 |
|
|
|
## 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: 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: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:| |
|
| 1.977 | 1.0 | 1531 | 1.3885 | 41.7045 | 23.3673 | 40.7292 | 40.6837 | |
|
| 1.4827 | 2.0 | 3062 | 1.2265 | 46.2602 | 27.7036 | 45.3412 | 45.3728 | |
|
| 1.2617 | 3.0 | 4593 | 1.0713 | 49.6738 | 32.0177 | 48.9186 | 48.9156 | |
|
| 1.1168 | 4.0 | 6124 | 0.9923 | 52.3824 | 35.7493 | 51.7434 | 51.706 | |
|
| 1.0041 | 5.0 | 7655 | 0.9439 | 55.6842 | 40.0864 | 54.9503 | 55.0016 | |
|
| 0.9305 | 6.0 | 9186 | 0.9085 | 56.5987 | 41.4443 | 55.9192 | 55.9222 | |
|
| 0.8763 | 7.0 | 10717 | 0.8974 | 57.2262 | 42.0378 | 56.5748 | 56.5201 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.28.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
