<!-- 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: 0.3423
- 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: 9
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.9781 | 1.0 | 318 | 2.1788 | 0.7426 |
1.6844 | 2.0 | 636 | 1.1132 | 0.8581 |
0.8838 | 3.0 | 954 | 0.6339 | 0.9145 |
0.5229 | 4.0 | 1272 | 0.4574 | 0.9332 |
0.3722 | 5.0 | 1590 | 0.3924 | 0.9432 |
0.3046 | 6.0 | 1908 | 0.3645 | 0.9458 |
0.2709 | 7.0 | 2226 | 0.3505 | 0.9465 |
0.2541 | 8.0 | 2544 | 0.3439 | 0.9468 |
0.2471 | 9.0 | 2862 | 0.3423 | 0.9477 |
Framework versions
- Transformers 4.16.2
- Pytorch 2.0.1+cu118
- Datasets 1.16.1
- Tokenizers 0.13.3