<!-- 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: 0.1003
- Accuracy: 0.9390
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 | 0.5736 | 0.7319 |
0.7584 | 2.0 | 636 | 0.2875 | 0.8816 |
0.7584 | 3.0 | 954 | 0.1812 | 0.9229 |
0.2802 | 4.0 | 1272 | 0.1391 | 0.9310 |
0.1604 | 5.0 | 1590 | 0.1212 | 0.9361 |
0.1604 | 6.0 | 1908 | 0.1115 | 0.9403 |
0.125 | 7.0 | 2226 | 0.1062 | 0.94 |
0.1099 | 8.0 | 2544 | 0.1028 | 0.9394 |
0.1099 | 9.0 | 2862 | 0.1011 | 0.9403 |
0.104 | 10.0 | 3180 | 0.1003 | 0.9390 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1
- Datasets 2.9.0
- Tokenizers 0.13.2