bnc_sh1_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.9223
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: 42
- 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 |
|---|---|---|---|
| 7.1746 | 1.0 | 392 | 6.4942 |
| 6.3041 | 2.0 | 784 | 6.2632 |
| 6.1373 | 3.0 | 1176 | 6.1577 |
| 6.0362 | 4.0 | 1568 | 6.0856 |
| 5.9565 | 5.0 | 1960 | 6.0312 |
| 5.8874 | 6.0 | 2352 | 5.9909 |
| 5.8242 | 7.0 | 2744 | 5.9565 |
| 5.7642 | 8.0 | 3136 | 5.9308 |
| 5.7061 | 9.0 | 3528 | 5.9118 |
| 5.6492 | 10.0 | 3920 | 5.8967 |
| 5.5937 | 11.0 | 4312 | 5.8873 |
| 5.5395 | 12.0 | 4704 | 5.8829 |
| 5.4877 | 13.0 | 5096 | 5.8853 |
| 5.4383 | 14.0 | 5488 | 5.8882 |
| 5.3921 | 15.0 | 5880 | 5.8946 |
| 5.3497 | 16.0 | 6272 | 5.9007 |
| 5.3118 | 17.0 | 6664 | 5.9079 |
| 5.2801 | 18.0 | 7056 | 5.9137 |
| 5.2551 | 19.0 | 7448 | 5.9190 |
| 5.2371 | 20.0 | 7840 | 5.9223 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0