---
tags:
- generated_from_trainer
datasets:
- samsum
model-index:
- name: pegasus-samsum-1
  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-samsum-1

This model is a fine-tuned version of [google/pegasus-cnn_dailymail](https://huggingface.co/google/pegasus-cnn_dailymail) on the samsum dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3783

## 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: 5e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 2
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.7182        | 0.07  | 500  | 1.6019          |
| 1.805         | 0.14  | 1000 | 1.5057          |
| 1.7421        | 0.2   | 1500 | 1.4710          |
| 1.4131        | 0.27  | 2000 | 1.4522          |
| 1.5483        | 0.34  | 2500 | 1.4422          |
| 1.2689        | 0.41  | 3000 | 1.4297          |
| 2.0376        | 0.48  | 3500 | 1.4136          |
| 1.5208        | 0.54  | 4000 | 1.4089          |
| 1.6772        | 0.61  | 4500 | 1.3973          |
| 1.5757        | 0.68  | 5000 | 1.3951          |
| 1.8022        | 0.75  | 5500 | 1.3846          |
| 1.6937        | 0.81  | 6000 | 1.3833          |
| 1.4412        | 0.88  | 6500 | 1.3820          |
| 1.4339        | 0.95  | 7000 | 1.3783          |


### Framework versions

- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2