wiki_np_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5824
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: 256
- eval_batch_size: 256
- seed: 30
- optimizer: Use 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: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 7.2503 | 1.0 | 399 | 6.5648 |
| 6.3058 | 2.0 | 798 | 6.1986 |
| 6.0421 | 3.0 | 1197 | 6.0220 |
| 5.8743 | 4.0 | 1596 | 5.8981 |
| 5.7397 | 5.0 | 1995 | 5.8011 |
| 5.6244 | 6.0 | 2394 | 5.7275 |
| 5.5233 | 7.0 | 2793 | 5.6738 |
| 5.4332 | 8.0 | 3192 | 5.6315 |
| 5.3508 | 9.0 | 3591 | 5.6029 |
| 5.2752 | 10.0 | 3990 | 5.5831 |
| 5.2046 | 11.0 | 4389 | 5.5690 |
| 5.1392 | 12.0 | 4788 | 5.5597 |
| 5.0772 | 13.0 | 5187 | 5.5574 |
| 5.0205 | 14.0 | 5586 | 5.5598 |
| 4.9708 | 15.0 | 5985 | 5.5633 |
| 4.9276 | 16.0 | 6384 | 5.5660 |
| 4.8901 | 17.0 | 6783 | 5.5705 |
| 4.8583 | 18.0 | 7182 | 5.5747 |
| 4.8322 | 19.0 | 7581 | 5.5800 |
| 4.8126 | 20.0 | 7980 | 5.5824 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0