<!-- 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-small-finetuned-billsum-ca_test
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.3376
- Rouge1: 12.6315
- Rouge2: 6.9839
- Rougel: 10.9983
- Rougelsum: 11.9383
- 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: 2
- eval_batch_size: 2
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 495 | 2.4805 | 9.9389 | 4.1239 | 8.3979 | 9.1599 | 19.0 |
| 3.1564 | 2.0 | 990 | 2.3833 | 12.1026 | 6.5196 | 10.5123 | 11.4527 | 19.0 |
| 2.66 | 3.0 | 1485 | 2.3496 | 12.5389 | 6.8686 | 10.8798 | 11.8636 | 19.0 |
| 2.5671 | 4.0 | 1980 | 2.3376 | 12.6315 | 6.9839 | 10.9983 | 11.9383 | 19.0 |
Framework versions
- Transformers 4.12.2
- Pytorch 1.9.0+cu111
- Datasets 1.14.0
- Tokenizers 0.10.3
