candor_w_30
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.9684
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 |
|---|---|---|---|
| 5.4118 | 1.0 | 423 | 4.2894 |
| 4.0599 | 2.0 | 846 | 4.0673 |
| 3.9233 | 3.0 | 1269 | 3.9972 |
| 3.8527 | 4.0 | 1692 | 3.9568 |
| 3.8008 | 5.0 | 2115 | 3.9300 |
| 3.757 | 6.0 | 2538 | 3.9101 |
| 3.7168 | 7.0 | 2961 | 3.8990 |
| 3.6791 | 8.0 | 3384 | 3.8893 |
| 3.6417 | 9.0 | 3807 | 3.8859 |
| 3.605 | 10.0 | 4230 | 3.8869 |
| 3.5681 | 11.0 | 4653 | 3.8877 |
| 3.5316 | 12.0 | 5076 | 3.8944 |
| 3.4947 | 13.0 | 5499 | 3.9034 |
| 3.4592 | 14.0 | 5922 | 3.9148 |
| 3.4253 | 15.0 | 6345 | 3.9225 |
| 3.3934 | 16.0 | 6768 | 3.9346 |
| 3.3629 | 17.0 | 7191 | 3.9462 |
| 3.3376 | 18.0 | 7614 | 3.9563 |
| 3.3165 | 19.0 | 8037 | 3.9642 |
| 3.3004 | 20.0 | 8460 | 3.9684 |
Framework versions
- Transformers 4.56.1
- Pytorch 2.8.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.0
- Downloads last month
- 16