my_awesome_billsum_model_test-1
This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:
- Loss: 2.5677
- Rouge1: 0.135
- Rouge2: 0.0426
- Rougel: 0.1108
- Rougelsum: 0.1109
- 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 |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 62 | 2.8609 | 0.1196 | 0.0301 | 0.1015 | 0.1014 | 19.0 |
| No log | 2.0 | 124 | 2.6490 | 0.1331 | 0.041 | 0.11 | 0.1103 | 19.0 |
| No log | 3.0 | 186 | 2.5855 | 0.1338 | 0.0418 | 0.1102 | 0.1102 | 19.0 |
| No log | 4.0 | 248 | 2.5677 | 0.135 | 0.0426 | 0.1108 | 0.1109 | 19.0 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3