metadata
base_model: google/pegasus-xsum
tags:
- generated_from_trainer
model-index:
- name: pegasus-legalease
results: []
pegasus-legalease
This model is a fine-tuned version of google/pegasus-xsum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.2285
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: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.09 | 250 | 4.6668 |
| 4.9697 | 0.18 | 500 | 4.1227 |
| 4.9697 | 0.27 | 750 | 1.4700 |
| 2.5705 | 0.36 | 1000 | 1.2933 |
| 2.5705 | 0.46 | 1250 | 1.2669 |
| 1.4047 | 0.55 | 1500 | 1.2507 |
| 1.4047 | 0.64 | 1750 | 1.2454 |
| 1.3544 | 0.73 | 2000 | 1.2566 |
| 1.3544 | 0.82 | 2250 | 1.2464 |
| 1.342 | 0.91 | 2500 | 1.2393 |
| 1.342 | 1.0 | 2750 | 1.2349 |
| 1.3258 | 1.09 | 3000 | 1.2312 |
| 1.3258 | 1.18 | 3250 | 1.2288 |
| 1.3196 | 1.27 | 3500 | 1.2258 |
| 1.3196 | 1.37 | 3750 | 1.2251 |
| 1.3233 | 1.46 | 4000 | 1.2233 |
| 1.3233 | 1.55 | 4250 | 1.2259 |
| 1.2873 | 1.64 | 4500 | 1.2274 |
| 1.2873 | 1.73 | 4750 | 1.2285 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2