candor_w_13
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.9709
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: 13
- 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 |
|---|---|---|---|
| 5.4142 | 1.0 | 423 | 4.2772 |
| 4.0569 | 2.0 | 846 | 4.0674 |
| 3.9211 | 3.0 | 1269 | 3.9982 |
| 3.8512 | 4.0 | 1692 | 3.9568 |
| 3.7997 | 5.0 | 2115 | 3.9299 |
| 3.7557 | 6.0 | 2538 | 3.9152 |
| 3.7157 | 7.0 | 2961 | 3.8975 |
| 3.6774 | 8.0 | 3384 | 3.8906 |
| 3.6403 | 9.0 | 3807 | 3.8858 |
| 3.6033 | 10.0 | 4230 | 3.8870 |
| 3.5665 | 11.0 | 4653 | 3.8902 |
| 3.5296 | 12.0 | 5076 | 3.8938 |
| 3.4931 | 13.0 | 5499 | 3.9042 |
| 3.4577 | 14.0 | 5922 | 3.9154 |
| 3.4232 | 15.0 | 6345 | 3.9273 |
| 3.3913 | 16.0 | 6768 | 3.9371 |
| 3.3608 | 17.0 | 7191 | 3.9483 |
| 3.3353 | 18.0 | 7614 | 3.9592 |
| 3.3142 | 19.0 | 8037 | 3.9672 |
| 3.2983 | 20.0 | 8460 | 3.9709 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 90