---
tags:
- generated_from_trainer
datasets:
- xsum
model-index:
- name: RoFormer_small-summarization
  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. -->

# RoFormer_small-summarization

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: 4.3373

## 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: 0.001
- 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: 100
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 4.975         | 1.0   | 5762  | 4.4897          |
| 4.4149        | 2.0   | 11525 | 4.3647          |
| 4.3296        | 3.0   | 17286 | 4.3373          |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0