t5-base-news_headlines
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0458
- Rouge1: 54.4139
- Rouge2: 37.646
- Rougel: 52.7585
- Rougelsum: 52.7718
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: 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 |
|---|---|---|---|---|---|---|---|
| 2.0018 | 1.0 | 1531 | 1.5329 | 43.1551 | 22.8869 | 40.7905 | 40.8246 |
| 1.574 | 2.0 | 3062 | 1.3419 | 46.5375 | 26.8791 | 44.41 | 44.4587 |
| 1.3702 | 3.0 | 4593 | 1.2201 | 48.6514 | 29.6228 | 46.6431 | 46.7098 |
| 1.2289 | 4.0 | 6124 | 1.1366 | 51.7488 | 33.7562 | 50.0123 | 50.0537 |
| 1.126 | 5.0 | 7655 | 1.0810 | 52.9846 | 35.6371 | 51.3321 | 51.3433 |
| 1.0569 | 6.0 | 9186 | 1.0585 | 53.8125 | 36.646 | 52.1451 | 52.1865 |
| 1.0105 | 7.0 | 10717 | 1.0458 | 54.4139 | 37.646 | 52.7585 | 52.7718 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3