<!-- 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: 0.1002
- Accuracy: 0.9419
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 |
---|---|---|---|---|
0.9029 | 1.0 | 318 | 0.5766 | 0.7216 |
0.4487 | 2.0 | 636 | 0.2855 | 0.8755 |
0.2535 | 3.0 | 954 | 0.1780 | 0.9287 |
0.1767 | 4.0 | 1272 | 0.1384 | 0.9319 |
0.142 | 5.0 | 1590 | 0.1212 | 0.9339 |
0.1245 | 6.0 | 1908 | 0.1115 | 0.9397 |
0.1143 | 7.0 | 2226 | 0.1058 | 0.9416 |
0.108 | 8.0 | 2544 | 0.1025 | 0.9423 |
0.1039 | 9.0 | 2862 | 0.1009 | 0.9423 |
0.102 | 10.0 | 3180 | 0.1002 | 0.9419 |
Framework versions
- Transformers 4.34.0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.14.1