viexdp-bartpho-word-src-tgt-5e-05-20261024072310
This model is a fine-tuned version of vinai/bartpho-word on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.6443
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0579 | 1.0 | 348 | 2.2445 |
| 1.6086 | 2.0 | 696 | 2.1662 |
| 1.0756 | 3.0 | 1044 | 2.2711 |
| 0.6564 | 4.0 | 1392 | 2.3500 |
| 0.3967 | 5.0 | 1740 | 2.4693 |
| 0.2507 | 6.0 | 2088 | 2.5805 |
| 0.1751 | 7.0 | 2436 | 2.5973 |
| 0.1194 | 8.0 | 2784 | 2.6443 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2