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: 1.3030
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 | 5.0879 |
| 5.3169 | 0.18 | 500 | 4.3939 |
| 5.3169 | 0.27 | 750 | 1.5484 |
| 2.6388 | 0.35 | 1000 | 1.3365 |
| 2.6388 | 0.44 | 1250 | 1.3390 |
| 1.4831 | 0.53 | 1500 | 1.3171 |
| 1.4831 | 0.62 | 1750 | 1.3076 |
| 1.4308 | 0.71 | 2000 | 1.3052 |
| 1.4308 | 0.8 | 2250 | 1.3040 |
| 1.4542 | 0.89 | 2500 | 1.3034 |
| 1.4542 | 0.98 | 2750 | 1.3030 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2