---
license: mit
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: ViT5_1024
  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. -->

# ViT5_1024

This model is a fine-tuned version of [VietAI/vit5-base-vietnews-summarization](https://huggingface.co/VietAI/vit5-base-vietnews-summarization) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5008
- Rouge-1: 0.3673
- Rouge-2: 0.2276
- Rouge-4: 0.1451
- Rouge-l: 0.3317
- Rouge-w-1.2: 0.1398
- Rouge-s4: 0.1853
- Rouge-su4: 0.2162
- R: 0.3044
- P: 0.463
- Bleu: 19.2804

## 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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- 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 | Rouge-1 | Rouge-2 | Rouge-4 | Rouge-l | Rouge-w-1.2 | Rouge-s4 | Rouge-su4 | R      | P      | Bleu    |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:-------:|:-----------:|:--------:|:---------:|:------:|:------:|:-------:|
| 0.5811        | 1.0   | 629  | 0.5152          | 0.2291  | 0.147   | 0.0963  | 0.2053  | 0.0868      | 0.1206   | 0.139     | 0.1836 | 0.3046 | 10.8017 |
| 0.5204        | 2.0   | 1258 | 0.5024          | 0.3559  | 0.2182  | 0.1371  | 0.3191  | 0.1355      | 0.1755   | 0.2061    | 0.2945 | 0.4495 | 18.7571 |
| 0.4607        | 3.0   | 1887 | 0.4984          | 0.3674  | 0.222   | 0.1374  | 0.329   | 0.1386      | 0.1787   | 0.2107    | 0.3108 | 0.4493 | 19.4123 |
| 0.4577        | 4.0   | 2516 | 0.5008          | 0.3673  | 0.2276  | 0.1451  | 0.3317  | 0.1398      | 0.1853   | 0.2162    | 0.3044 | 0.463  | 19.2804 |


### Framework versions

- Transformers 4.26.1
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3