bnc_o_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.3416
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 |
|---|---|---|---|
| 6.8393 | 1.0 | 391 | 5.7447 |
| 5.3976 | 2.0 | 782 | 5.1813 |
| 5.0032 | 3.0 | 1173 | 4.9295 |
| 4.7792 | 4.0 | 1564 | 4.7712 |
| 4.6136 | 5.0 | 1955 | 4.6575 |
| 4.4794 | 6.0 | 2346 | 4.5687 |
| 4.3645 | 7.0 | 2737 | 4.5038 |
| 4.2636 | 8.0 | 3128 | 4.4510 |
| 4.173 | 9.0 | 3519 | 4.4146 |
| 4.09 | 10.0 | 3910 | 4.3859 |
| 4.016 | 11.0 | 4301 | 4.3664 |
| 3.9493 | 12.0 | 4692 | 4.3526 |
| 3.8894 | 13.0 | 5083 | 4.3425 |
| 3.8358 | 14.0 | 5474 | 4.3372 |
| 3.7876 | 15.0 | 5865 | 4.3352 |
| 3.7442 | 16.0 | 6256 | 4.3358 |
| 3.7063 | 17.0 | 6647 | 4.3362 |
| 3.6736 | 18.0 | 7038 | 4.3378 |
| 3.6464 | 19.0 | 7429 | 4.3405 |
| 3.626 | 20.0 | 7820 | 4.3416 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0