kd-distilBERT-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: 0.7752
- Accuracy: 0.9129
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 4.3211 | 1.0 | 318 | 3.3313 | 0.7235 |
| 2.6568 | 2.0 | 636 | 1.9016 | 0.8452 |
| 1.5575 | 3.0 | 954 | 1.1668 | 0.8955 |
| 1.0094 | 4.0 | 1272 | 0.8619 | 0.9087 |
| 0.7914 | 5.0 | 1590 | 0.7752 | 0.9129 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.12.1+cu113
- Datasets 2.7.0
- Tokenizers 0.13.2