distilbert-frugal-ai-challenge
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2701
- Accuracy: 0.6850
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: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 305 | 1.0953 | 0.6169 |
| 1.2133 | 2.0 | 610 | 0.9744 | 0.6604 |
| 1.2133 | 3.0 | 915 | 0.9648 | 0.6809 |
| 0.5996 | 4.0 | 1220 | 1.1174 | 0.6710 |
| 0.2747 | 5.0 | 1525 | 1.3065 | 0.6538 |
| 0.2747 | 6.0 | 1830 | 1.5355 | 0.6637 |
| 0.0989 | 7.0 | 2135 | 1.7344 | 0.6579 |
| 0.0989 | 8.0 | 2440 | 1.7971 | 0.6735 |
| 0.0493 | 9.0 | 2745 | 1.9623 | 0.6727 |
| 0.0254 | 10.0 | 3050 | 2.0073 | 0.6776 |
| 0.0254 | 11.0 | 3355 | 2.0603 | 0.6833 |
| 0.0163 | 12.0 | 3660 | 2.1403 | 0.6784 |
| 0.0163 | 13.0 | 3965 | 2.1846 | 0.6792 |
| 0.0133 | 14.0 | 4270 | 2.2136 | 0.6776 |
| 0.0069 | 15.0 | 4575 | 2.2117 | 0.6833 |
| 0.0069 | 16.0 | 4880 | 2.2279 | 0.6776 |
| 0.0072 | 17.0 | 5185 | 2.2685 | 0.6809 |
| 0.0072 | 18.0 | 5490 | 2.2847 | 0.6809 |
| 0.0037 | 19.0 | 5795 | 2.2697 | 0.6809 |
| 0.0035 | 20.0 | 6100 | 2.2701 | 0.6850 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0