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: 0.0264
- Sacrebleu: 97.6953
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: 24
- eval_batch_size: 96
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- 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 | Sacrebleu |
|---|---|---|---|---|
| No log | 1.0 | 179 | 0.0553 | 95.6246 |
| No log | 2.0 | 358 | 0.0381 | 96.6791 |
| 0.0931 | 3.0 | 537 | 0.0297 | 97.3944 |
| 0.0931 | 4.0 | 716 | 0.0270 | 97.5658 |
| 0.0931 | 5.0 | 895 | 0.0264 | 97.6953 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.0
- Datasets 3.1.0
- Tokenizers 0.20.3