viexdp-bartpho-word-sft-baseline-5e-05-20261024082731
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: 2.6390
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 |
|---|---|---|---|
| 2.0665 | 1.0 | 348 | 2.2169 |
| 1.6192 | 2.0 | 696 | 2.1817 |
| 1.0784 | 3.0 | 1044 | 2.2550 |
| 0.6513 | 4.0 | 1392 | 2.3654 |
| 0.3913 | 5.0 | 1740 | 2.4497 |
| 0.2473 | 6.0 | 2088 | 2.5583 |
| 0.1702 | 7.0 | 2436 | 2.6147 |
| 0.1171 | 8.0 | 2784 | 2.6390 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.11.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2