candor_np_42
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 4.4615
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 |
|---|---|---|---|
| 5.7526 | 1.0 | 422 | 4.7797 |
| 4.6298 | 2.0 | 844 | 4.6014 |
| 4.5097 | 3.0 | 1266 | 4.5212 |
| 4.4386 | 4.0 | 1688 | 4.4750 |
| 4.3849 | 5.0 | 2110 | 4.4444 |
| 4.3394 | 6.0 | 2532 | 4.4171 |
| 4.2978 | 7.0 | 2954 | 4.4004 |
| 4.2588 | 8.0 | 3376 | 4.3882 |
| 4.2204 | 9.0 | 3798 | 4.3792 |
| 4.1823 | 10.0 | 4220 | 4.3779 |
| 4.1437 | 11.0 | 4642 | 4.3806 |
| 4.1048 | 12.0 | 5064 | 4.3839 |
| 4.0663 | 13.0 | 5486 | 4.3925 |
| 4.0284 | 14.0 | 5908 | 4.4012 |
| 3.9919 | 15.0 | 6330 | 4.4138 |
| 3.9575 | 16.0 | 6752 | 4.4268 |
| 3.9258 | 17.0 | 7174 | 4.4385 |
| 3.8983 | 18.0 | 7596 | 4.4478 |
| 3.876 | 19.0 | 8018 | 4.4578 |
| 3.8594 | 20.0 | 8440 | 4.4615 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 465