bartede
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: 0.5850
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- 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
- lr_scheduler_warmup_steps: 0.06
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.9411 | 1.0 | 158 | 0.8584 |
| 5.7966 | 2.0 | 316 | 0.6884 |
| 4.6457 | 3.0 | 474 | 0.6328 |
| 4.1820 | 4.0 | 632 | 0.6210 |
| 3.8281 | 5.0 | 790 | 0.5837 |
| 2.7451 | 6.0 | 948 | 0.5861 |
| 2.3142 | 7.0 | 1106 | 0.6141 |
| 1.8199 | 8.0 | 1264 | 0.6588 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 502
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support