---
license: mit
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Vi-gec5
  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. -->

# Vi-gec5

This model is a fine-tuned version of [VietAI/vit5-base](https://huggingface.co/VietAI/vit5-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0927
- Wer: 2.9213

## 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-06
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1167
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.7673        | 0.41  | 233  | 0.6208          | 191.2360 |
| 0.4518        | 0.81  | 466  | 0.1819          | 34.3105  |
| 0.2424        | 1.22  | 699  | 0.1073          | 4.2510   |
| 0.2037        | 1.63  | 932  | 0.0955          | 3.2135   |
| 0.1995        | 2.04  | 1165 | 0.0927          | 2.9213   |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2