<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-distilled-clinc
This model is a fine-tuned version of distilbert-base-uncased on the clinc_oos dataset. It achieves the following results on the evaluation set:
- Loss: 0.2192
- 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.8173 | 1.0 | 318 | 1.2393 | 0.7426 |
| 0.9618 | 2.0 | 636 | 0.6148 | 0.8590 |
| 0.5073 | 3.0 | 954 | 0.3621 | 0.9158 |
| 0.3189 | 4.0 | 1272 | 0.2748 | 0.9319 |
| 0.2442 | 5.0 | 1590 | 0.2454 | 0.9394 |
| 0.2143 | 6.0 | 1908 | 0.2330 | 0.9419 |
| 0.1987 | 7.0 | 2226 | 0.2258 | 0.9432 |
| 0.1905 | 8.0 | 2544 | 0.2218 | 0.9442 |
| 0.1861 | 9.0 | 2862 | 0.2201 | 0.9439 |
| 0.1836 | 10.0 | 3180 | 0.2192 | 0.9439 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
