<!-- 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. -->
my_awesome_billsum_model
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1531
- Rouge1: 0.1799
- Rouge2: 0.1086
- Rougel: 0.1599
- Rougelsum: 0.1598
- Gen Len: 19.0
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 0.2365 | 1.0 | 1635 | 0.1723 | 0.1782 | 0.1055 | 0.1575 | 0.1575 | 19.0 |
| 0.209 | 2.0 | 3270 | 0.1596 | 0.1787 | 0.1067 | 0.1584 | 0.1584 | 19.0 |
| 0.1986 | 3.0 | 4905 | 0.1545 | 0.1794 | 0.1079 | 0.1593 | 0.1593 | 19.0 |
| 0.1917 | 4.0 | 6540 | 0.1531 | 0.1799 | 0.1086 | 0.1599 | 0.1598 | 19.0 |
Framework versions
- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2
