---
tags:
- generated_from_trainer
model-index:
- name: Pegasus_paraphraser_2
  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_paraphraser_2

This model is a fine-tuned version of [Gayathri142214002/Pegasus_paraphraser_1](https://huggingface.co/Gayathri142214002/Pegasus_paraphraser_1) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2781

## 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: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.2589        | 0.45  | 1000 | 0.2488          |
| 0.2693        | 0.9   | 2000 | 0.2436          |
| 0.2255        | 1.35  | 3000 | 0.2632          |
| 0.2291        | 1.8   | 4000 | 0.2603          |
| 0.2092        | 2.25  | 5000 | 0.2714          |
| 0.1955        | 2.69  | 6000 | 0.2668          |
| 0.1893        | 3.14  | 7000 | 0.2802          |
| 0.1706        | 3.59  | 8000 | 0.2781          |


### Framework versions

- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3