metadata
tags:
- generated_from_trainer
model-index:
- name: pegasus-legalease
results: []
datasets:
- hheiden/us-congress-117-bills
language:
- en
metrics:
- rouge
library_name: transformers
pegasus-legalease
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Rouge1: 0.4632
- Rouge2: 0.3210
- RougeL: 0.4055
- Rougelsum: 0.4196
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.09 | 250 | 4.5607 |
| 4.8769 | 0.18 | 500 | 4.2187 |
| 4.8769 | 0.27 | 750 | 2.2905 |
| 2.9804 | 0.35 | 1000 | 1.1894 |
| 2.9804 | 0.44 | 1250 | 1.1604 |
| 1.3716 | 0.53 | 1500 | 1.1433 |
| 1.3716 | 0.62 | 1750 | 1.1318 |
| 1.2964 | 0.71 | 2000 | 1.1244 |
| 1.2964 | 0.8 | 2250 | 1.1188 |
| 1.248 | 0.89 | 2500 | 1.1152 |
| 1.248 | 0.98 | 2750 | 1.1142 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2