metadata
library_name: transformers
license: mit
base_model: vinai/bartpho-syllable-base
tags:
- text2text-generation
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: vinh-test
results: []
vinh-test
This model is a fine-tuned version of vinai/bartpho-syllable-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3488
- Model Preparation Time: 0.0071
- Sacrebleu: 92.9401
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: 12
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Sacrebleu |
|---|---|---|---|---|---|
| No log | 0.9231 | 3 | 0.7367 | 0.0071 | 89.5419 |
| No log | 1.8462 | 6 | 0.6013 | 0.0071 | 89.5419 |
| No log | 2.7692 | 9 | 0.4542 | 0.0071 | 89.5419 |
| No log | 4.0 | 13 | 0.3624 | 0.0071 | 92.9401 |
| No log | 4.6154 | 15 | 0.3488 | 0.0071 | 92.9401 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3