metadata
library_name: transformers
license: mit
base_model: vinai/bartpho-syllable
tags:
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: BARTBana_Translation_Finetune_v0
results: []
BARTBana_Translation_Finetune_v0
This model is a fine-tuned version of vinai/bartpho-syllable on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4266
- Sacrebleu: 2.9607
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: 2e-05
- train_batch_size: 100
- eval_batch_size: 100
- seed: 42
- optimizer: Use OptimizerNames.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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|---|---|---|---|---|
| 0.8315 | 1.0 | 429 | 0.6994 | 1.5712 |
| 0.7319 | 2.0 | 858 | 0.6374 | 2.6693 |
| 0.6676 | 3.0 | 1287 | 0.5882 | 4.0478 |
| 0.6199 | 4.0 | 1716 | 0.5549 | 4.4905 |
| 0.5912 | 5.0 | 2145 | 0.5353 | 5.0681 |
| 0.5583 | 6.0 | 2574 | 0.5219 | 5.7212 |
| 0.5488 | 7.0 | 3003 | 0.5117 | 6.1119 |
| 0.5294 | 8.0 | 3432 | 0.5052 | 5.9770 |
| 0.5227 | 9.0 | 3861 | 0.5020 | 6.2340 |
| 0.5113 | 10.0 | 4290 | 0.5011 | 6.2681 |
Framework versions
- Transformers 4.48.1
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0