wiki_w_51
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.4182
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: 51
- 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 |
|---|---|---|---|
| 7.063 | 1.0 | 400 | 6.1963 |
| 5.9603 | 2.0 | 800 | 5.8568 |
| 5.7367 | 3.0 | 1200 | 5.7185 |
| 5.6043 | 4.0 | 1600 | 5.6255 |
| 5.4977 | 5.0 | 2000 | 5.5538 |
| 5.405 | 6.0 | 2400 | 5.4988 |
| 5.3231 | 7.0 | 2800 | 5.4586 |
| 5.2489 | 8.0 | 3200 | 5.4297 |
| 5.1805 | 9.0 | 3600 | 5.4079 |
| 5.1167 | 10.0 | 4000 | 5.3956 |
| 5.0566 | 11.0 | 4400 | 5.3880 |
| 4.9995 | 12.0 | 4800 | 5.3855 |
| 4.9456 | 13.0 | 5200 | 5.3854 |
| 4.8941 | 14.0 | 5600 | 5.3895 |
| 4.8489 | 15.0 | 6000 | 5.3983 |
| 4.8092 | 16.0 | 6400 | 5.3998 |
| 4.7745 | 17.0 | 6800 | 5.4053 |
| 4.745 | 18.0 | 7200 | 5.4123 |
| 4.7208 | 19.0 | 7600 | 5.4157 |
| 4.7025 | 20.0 | 8000 | 5.4182 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0