|
--- |
|
base_model: google/pegasus-xsum |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: pegasus-legalease |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# pegasus-legalease |
|
|
|
This model is a fine-tuned version of [google/pegasus-xsum](https://huggingface.co/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 |
|
|