my_awesome_model
This model is a fine-tuned version of distilbert/distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7306
- F1: 0.7462
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 123
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.2968 | 1.0 | 1276 | 0.2712 | 0.6331 |
| 0.2219 | 2.0 | 2552 | 0.2628 | 0.6895 |
| 0.1707 | 3.0 | 3828 | 0.2709 | 0.7036 |
| 0.1306 | 4.0 | 5104 | 0.3581 | 0.7073 |
| 0.105 | 5.0 | 6380 | 0.3580 | 0.7335 |
| 0.0792 | 6.0 | 7656 | 0.4139 | 0.7168 |
| 0.0591 | 7.0 | 8932 | 0.4728 | 0.7364 |
| 0.0594 | 8.0 | 10208 | 0.4109 | 0.7188 |
| 0.0484 | 9.0 | 11484 | 0.5309 | 0.7159 |
| 0.0506 | 10.0 | 12760 | 0.5631 | 0.7226 |
| 0.0379 | 11.0 | 14036 | 0.6407 | 0.7233 |
| 0.0315 | 12.0 | 15312 | 0.6281 | 0.7355 |
| 0.0342 | 13.0 | 16588 | 0.6942 | 0.7286 |
| 0.0284 | 14.0 | 17864 | 0.6880 | 0.7229 |
| 0.0338 | 15.0 | 19140 | 0.6297 | 0.7333 |
| 0.0242 | 16.0 | 20416 | 0.6048 | 0.7277 |
| 0.026 | 17.0 | 21692 | 0.6959 | 0.7342 |
| 0.0198 | 18.0 | 22968 | 0.6872 | 0.7341 |
| 0.0188 | 19.0 | 24244 | 0.6810 | 0.7435 |
| 0.0136 | 20.0 | 25520 | 0.6943 | 0.7338 |
| 0.0174 | 21.0 | 26796 | 0.7095 | 0.7267 |
| 0.0119 | 22.0 | 28072 | 0.7306 | 0.7462 |
| 0.0131 | 23.0 | 29348 | 0.7683 | 0.7370 |
| 0.012 | 24.0 | 30624 | 0.7878 | 0.7193 |
| 0.0109 | 25.0 | 31900 | 0.7770 | 0.7332 |
| 0.0095 | 26.0 | 33176 | 0.7889 | 0.7318 |
| 0.0103 | 27.0 | 34452 | 0.8115 | 0.7326 |
| 0.0068 | 28.0 | 35728 | 0.8136 | 0.7341 |
| 0.0077 | 29.0 | 37004 | 0.8175 | 0.7361 |
| 0.0077 | 30.0 | 38280 | 0.8192 | 0.7364 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1