t5-base-billsum
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.6188
- Rouge1: 51.4114
- Rouge2: 30.6521
- Rougel: 40.9417
- Rougelsum: 44.6839
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 1.9236 | 1.0 | 1185 | 1.5895 | 52.5513 | 32.239 | 42.0215 | 45.9665 |
| 1.7231 | 2.0 | 2370 | 1.5380 | 53.3168 | 33.2784 | 42.9286 | 46.7854 |
| 1.6708 | 3.0 | 3555 | 1.5187 | 53.2982 | 33.3262 | 42.979 | 46.8863 |
| 1.7884 | 4.0 | 4740 | 1.6197 | 51.4854 | 30.768 | 41.0231 | 44.7727 |
| 1.8212 | 5.0 | 5925 | 1.6188 | 51.4114 | 30.6521 | 40.9417 | 44.6839 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.2
- Tokenizers 0.19.1