distilbert-base-uncased-distilled
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: 0.2061
- Accuracy: 0.9448
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 |
---|---|---|---|---|
1.7308 | 1.0 | 318 | 1.1633 | 0.7394 |
0.8985 | 2.0 | 636 | 0.5726 | 0.8635 |
0.4735 | 3.0 | 954 | 0.3350 | 0.9187 |
0.298 | 4.0 | 1272 | 0.2562 | 0.9361 |
0.2313 | 5.0 | 1590 | 0.2304 | 0.9413 |
0.2043 | 6.0 | 1908 | 0.2190 | 0.9432 |
0.1904 | 7.0 | 2226 | 0.2130 | 0.9445 |
0.1829 | 8.0 | 2544 | 0.2091 | 0.9442 |
0.1782 | 9.0 | 2862 | 0.2066 | 0.9455 |
0.1762 | 10.0 | 3180 | 0.2061 | 0.9448 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.10.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1
- Downloads last month
- 4
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.