<!-- 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 billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.1970
- Rouge1: 0.2001
- Rouge2: 0.1053
- Rougel: 0.1716
- Rougelsum: 0.1717
- 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: 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 124 | 2.5355 | 0.1414 | 0.0544 | 0.1183 | 0.1182 | 19.0 |
| No log | 2.0 | 248 | 2.3807 | 0.1674 | 0.0738 | 0.1416 | 0.1412 | 19.0 |
| No log | 3.0 | 372 | 2.3128 | 0.1977 | 0.1007 | 0.1695 | 0.1697 | 19.0 |
| No log | 4.0 | 496 | 2.2729 | 0.1987 | 0.1008 | 0.1695 | 0.1694 | 19.0 |
| 2.8078 | 5.0 | 620 | 2.2460 | 0.1997 | 0.1025 | 0.1707 | 0.1707 | 19.0 |
| 2.8078 | 6.0 | 744 | 2.2251 | 0.2011 | 0.1034 | 0.1715 | 0.1714 | 19.0 |
| 2.8078 | 7.0 | 868 | 2.2133 | 0.2016 | 0.1049 | 0.172 | 0.172 | 19.0 |
| 2.8078 | 8.0 | 992 | 2.2035 | 0.2018 | 0.1062 | 0.1723 | 0.1725 | 19.0 |
| 2.4762 | 9.0 | 1116 | 2.1985 | 0.2008 | 0.1059 | 0.172 | 0.1723 | 19.0 |
| 2.4762 | 10.0 | 1240 | 2.1970 | 0.2001 | 0.1053 | 0.1716 | 0.1717 | 19.0 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
