metadata
library_name: transformers
license: mit
base_model: vinai/bartpho-syllable
tags:
- generated_from_trainer
model-index:
- name: BartTay
results: []
BartTay
This model is a fine-tuned version of vinai/bartpho-syllable on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.7854
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 46 | 5.9329 |
| No log | 2.0 | 92 | 5.7500 |
| No log | 3.0 | 138 | 5.6268 |
| No log | 4.0 | 184 | 5.4371 |
| No log | 5.0 | 230 | 5.1383 |
| No log | 6.0 | 276 | 5.0149 |
| No log | 7.0 | 322 | 4.9770 |
| No log | 8.0 | 368 | 4.9059 |
| No log | 9.0 | 414 | 4.7860 |
| No log | 10.0 | 460 | 4.6284 |
| 5.4791 | 11.0 | 506 | 4.6639 |
| 5.4791 | 12.0 | 552 | 4.6550 |
| 5.4791 | 13.0 | 598 | 4.7702 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 3.1.0
- Tokenizers 0.22.1