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: 0.3462
- Accuracy: 0.9487
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 |
---|---|---|---|---|
No log | 1.0 | 318 | 2.4449 | 0.7529 |
2.8785 | 2.0 | 636 | 1.2330 | 0.8561 |
2.8785 | 3.0 | 954 | 0.6774 | 0.9132 |
1.0817 | 4.0 | 1272 | 0.4716 | 0.9335 |
0.454 | 5.0 | 1590 | 0.4020 | 0.9442 |
0.454 | 6.0 | 1908 | 0.3749 | 0.9439 |
0.294 | 7.0 | 2226 | 0.3593 | 0.9481 |
0.2429 | 8.0 | 2544 | 0.3514 | 0.9474 |
0.2429 | 9.0 | 2862 | 0.3486 | 0.9481 |
0.2258 | 10.0 | 3180 | 0.3462 | 0.9487 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 7
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.