bnc_np_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 5.5661
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 |
|---|---|---|---|
| 7.1048 | 1.0 | 392 | 6.3184 |
| 6.0953 | 2.0 | 784 | 6.0224 |
| 5.8828 | 3.0 | 1176 | 5.8840 |
| 5.7522 | 4.0 | 1568 | 5.7908 |
| 5.6486 | 5.0 | 1960 | 5.7201 |
| 5.5595 | 6.0 | 2352 | 5.6646 |
| 5.4785 | 7.0 | 2744 | 5.6209 |
| 5.4038 | 8.0 | 3136 | 5.5882 |
| 5.3331 | 9.0 | 3528 | 5.5620 |
| 5.266 | 10.0 | 3920 | 5.5466 |
| 5.2021 | 11.0 | 4312 | 5.5379 |
| 5.1415 | 12.0 | 4704 | 5.5326 |
| 5.0838 | 13.0 | 5096 | 5.5337 |
| 5.0289 | 14.0 | 5488 | 5.5361 |
| 4.9795 | 15.0 | 5880 | 5.5408 |
| 4.9362 | 16.0 | 6272 | 5.5467 |
| 4.8987 | 17.0 | 6664 | 5.5530 |
| 4.8673 | 18.0 | 7056 | 5.5596 |
| 4.8417 | 19.0 | 7448 | 5.5633 |
| 4.8227 | 20.0 | 7840 | 5.5661 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0