metadata
library_name: transformers
license: mit
base_model: VietAI/vit5-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
model-index:
- name: ViNormT5
results: []
ViNormT5
This model is a fine-tuned version of VietAI/vit5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2178
- Bleu Score: 78.7261
- Precision: 54.5998
- Recall: 54.5998
- Gen Len: 12.7826
- Err: 54.5998
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu Score | Precision | Recall | Gen Len | Err |
|---|---|---|---|---|---|---|---|---|
| 0.4635 | 1.0 | 419 | 0.2255 | 77.2678 | 49.5818 | 49.5818 | 12.7969 | 49.5818 |
| 0.166 | 2.0 | 838 | 0.2026 | 78.2851 | 53.1661 | 53.1661 | 12.8041 | 53.1661 |
| 0.0752 | 3.0 | 1257 | 0.2178 | 78.7261 | 54.5998 | 54.5998 | 12.7826 | 54.5998 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0