distilbert-base-uncased-distilled-clinc
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: 0.2784
- Accuracy: 0.9439
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: 48
- eval_batch_size: 48
- seed: 42
- optimizer: Use 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: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.2676 | 1.0 | 318 | 1.6183 | 0.7313 |
| 1.2618 | 2.0 | 636 | 0.8348 | 0.8623 |
| 0.6798 | 3.0 | 954 | 0.4896 | 0.9161 |
| 0.4213 | 4.0 | 1272 | 0.3648 | 0.9310 |
| 0.3106 | 5.0 | 1590 | 0.3145 | 0.9394 |
| 0.263 | 6.0 | 1908 | 0.2950 | 0.9406 |
| 0.2407 | 7.0 | 2226 | 0.2852 | 0.9426 |
| 0.2291 | 8.0 | 2544 | 0.2812 | 0.9432 |
| 0.2238 | 9.0 | 2862 | 0.2784 | 0.9439 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.7.1+cu118
- Datasets 4.5.0
- Tokenizers 0.22.2