<!-- 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: 0.2310
- Accuracy: 0.9471
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 |
|---|---|---|---|---|
| 1.9114 | 1.0 | 318 | 1.3130 | 0.7287 |
| 1.017 | 2.0 | 636 | 0.6531 | 0.8623 |
| 0.5374 | 3.0 | 954 | 0.3855 | 0.9148 |
| 0.3357 | 4.0 | 1272 | 0.2907 | 0.9339 |
| 0.2565 | 5.0 | 1590 | 0.2598 | 0.9406 |
| 0.2232 | 6.0 | 1908 | 0.2453 | 0.9452 |
| 0.2072 | 7.0 | 2226 | 0.2378 | 0.9465 |
| 0.1979 | 8.0 | 2544 | 0.2339 | 0.9465 |
| 0.1928 | 9.0 | 2862 | 0.2318 | 0.9461 |
| 0.1906 | 10.0 | 3180 | 0.2310 | 0.9471 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.12.1
- Datasets 1.16.1
- Tokenizers 0.10.3
