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: 4.6886
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 | 45 | 5.9733 |
| No log | 2.0 | 90 | 5.9003 |
| No log | 3.0 | 135 | 5.6155 |
| No log | 4.0 | 180 | 5.5120 |
| No log | 5.0 | 225 | 5.4180 |
| No log | 6.0 | 270 | 5.1716 |
| No log | 7.0 | 315 | 5.2570 |
| No log | 8.0 | 360 | 5.0764 |
| No log | 9.0 | 405 | 4.9511 |
| No log | 10.0 | 450 | 4.8147 |
| No log | 11.0 | 495 | 4.6616 |
| 5.5211 | 12.0 | 540 | 4.7865 |
| 5.5211 | 13.0 | 585 | 4.7858 |
| 5.5211 | 14.0 | 630 | 4.7064 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 3.1.0
- Tokenizers 0.22.1
- Downloads last month
- 12
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support