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: 0.0999
- Accuracy: 0.9406
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 |
---|---|---|---|---|
0.9039 | 1.0 | 318 | 0.5777 | 0.7348 |
0.4491 | 2.0 | 636 | 0.2863 | 0.8845 |
0.2533 | 3.0 | 954 | 0.1794 | 0.9216 |
0.1766 | 4.0 | 1272 | 0.1386 | 0.93 |
0.1416 | 5.0 | 1590 | 0.1208 | 0.9355 |
0.1244 | 6.0 | 1908 | 0.1111 | 0.94 |
0.1138 | 7.0 | 2226 | 0.1057 | 0.9397 |
0.1073 | 8.0 | 2544 | 0.1024 | 0.9410 |
0.1035 | 9.0 | 2862 | 0.1005 | 0.9410 |
0.1019 | 10.0 | 3180 | 0.0999 | 0.9406 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1+cu118
- Datasets 1.16.1
- Tokenizers 0.14.0
- Downloads last month
- 30
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.