billsum-t5-small
This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4770
- Rouge1: 0.1552
- Rouge2: 0.059
- Rougel: 0.1275
- Rougelsum: 0.1275
- 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 | 2.6042 | 0.1399 | 0.0499 | 0.1148 | 0.1145 | 19.0 |
| No log | 2.0 | 124 | 2.5220 | 0.1478 | 0.0538 | 0.1203 | 0.1202 | 19.0 |
| No log | 3.0 | 186 | 2.4874 | 0.1544 | 0.0581 | 0.1266 | 0.1265 | 19.0 |
| No log | 4.0 | 248 | 2.4770 | 0.1552 | 0.059 | 0.1275 | 0.1275 | 19.0 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1