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: 0.1192
- Accuracy: 0.9416
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 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 318 | 0.7137 | 0.7071 |
| 0.9882 | 2.0 | 636 | 0.3072 | 0.8710 |
| 0.9882 | 3.0 | 954 | 0.1833 | 0.9126 |
| 0.3074 | 4.0 | 1272 | 0.1479 | 0.9316 |
| 0.1659 | 5.0 | 1590 | 0.1344 | 0.9323 |
| 0.1659 | 6.0 | 1908 | 0.1278 | 0.9377 |
| 0.1351 | 7.0 | 2226 | 0.1240 | 0.9394 |
| 0.1231 | 8.0 | 2544 | 0.1210 | 0.9413 |
| 0.1231 | 9.0 | 2862 | 0.1198 | 0.9432 |
| 0.1184 | 10.0 | 3180 | 0.1192 | 0.9416 |
Framework versions
- Transformers 4.57.6
- Pytorch 2.10.0+cu126
- Datasets 4.8.4
- Tokenizers 0.22.2