---
library_name: peft
tags:
- generated_from_trainer
base_model: google/pegasus-xsum
model-index:
- name: T5-lora-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. -->

# T5-lora-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: 3.5452

## 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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- 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        | 0.18  | 250  | 4.1826          |
| 4.6756        | 0.35  | 500  | 3.8860          |
| 4.6756        | 0.53  | 750  | 3.7923          |
| 3.8476        | 0.71  | 1000 | 3.7309          |
| 3.8476        | 0.89  | 1250 | 3.6762          |
| 3.7406        | 1.06  | 1500 | 3.6374          |
| 3.7406        | 1.24  | 1750 | 3.6072          |
| 3.6278        | 1.42  | 2000 | 3.5841          |
| 3.6278        | 1.6   | 2250 | 3.5630          |
| 3.6359        | 1.77  | 2500 | 3.5509          |
| 3.6359        | 1.95  | 2750 | 3.5452          |


### Framework versions

- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2