<!-- 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: 0.1603
- Accuracy: 0.9477
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 |
---|---|---|---|---|
1.5224 | 1.0 | 318 | 1.0565 | 0.7629 |
0.8226 | 2.0 | 636 | 0.5476 | 0.8858 |
0.4473 | 3.0 | 954 | 0.3175 | 0.9226 |
0.2765 | 4.0 | 1272 | 0.2272 | 0.9368 |
0.2022 | 5.0 | 1590 | 0.1933 | 0.9410 |
0.1699 | 6.0 | 1908 | 0.1770 | 0.9465 |
0.1521 | 7.0 | 2226 | 0.1679 | 0.9474 |
0.142 | 8.0 | 2544 | 0.1637 | 0.9474 |
0.1362 | 9.0 | 2862 | 0.1613 | 0.9481 |
0.1339 | 10.0 | 3180 | 0.1603 | 0.9477 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2