|
--- |
|
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: 1.0569 |
|
|
|
## 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 | 4.5676 | |
|
| 4.9309 | 0.18 | 500 | 4.1409 | |
|
| 4.9309 | 0.27 | 750 | 1.9459 | |
|
| 2.7387 | 0.35 | 1000 | 1.1953 | |
|
| 2.7387 | 0.44 | 1250 | 1.1557 | |
|
| 1.3603 | 0.53 | 1500 | 1.1350 | |
|
| 1.3603 | 0.62 | 1750 | 1.1189 | |
|
| 1.2237 | 0.71 | 2000 | 1.1092 | |
|
| 1.2237 | 0.8 | 2250 | 1.0976 | |
|
| 1.2113 | 0.89 | 2500 | 1.0931 | |
|
| 1.2113 | 0.98 | 2750 | 1.0854 | |
|
| 1.2057 | 1.06 | 3000 | 1.0787 | |
|
| 1.2057 | 1.15 | 3250 | 1.0759 | |
|
| 1.1613 | 1.24 | 3500 | 1.0714 | |
|
| 1.1613 | 1.33 | 3750 | 1.0680 | |
|
| 1.1379 | 1.42 | 4000 | 1.0662 | |
|
| 1.1379 | 1.51 | 4250 | 1.0634 | |
|
| 1.163 | 1.6 | 4500 | 1.0622 | |
|
| 1.163 | 1.68 | 4750 | 1.0600 | |
|
| 1.1271 | 1.77 | 5000 | 1.0587 | |
|
| 1.1271 | 1.86 | 5250 | 1.0574 | |
|
| 1.1358 | 1.95 | 5500 | 1.0569 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
