---
tags:
- generated_from_trainer
datasets:
- xsum
model-index:
- name: retnet-xsum
  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. -->

# retnet-xsum

This model is a fine-tuned version of [](https://huggingface.co/) on the xsum dataset.
It achieves the following results on the evaluation set:
- Loss: 4.0200

## 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: 0.0006
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 8
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 5.3257        | 1.0   | 2187  | 4.6412          |
| 4.5863        | 2.0   | 4375  | 4.3474          |
| 4.3703        | 3.0   | 6562  | 4.2111          |
| 4.2404        | 4.0   | 8750  | 4.1213          |
| 4.1568        | 5.0   | 10937 | 4.0673          |
| 4.0975        | 6.0   | 13125 | 4.0371          |
| 4.0618        | 7.0   | 15312 | 4.0219          |
| 4.045         | 8.0   | 17496 | 4.0200          |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1