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: 0.3448
- Accuracy: 0.9497
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 | 2.4732 | 0.7284 |
2.9195 | 2.0 | 636 | 1.2381 | 0.8626 |
2.9195 | 3.0 | 954 | 0.6700 | 0.9171 |
1.0799 | 4.0 | 1272 | 0.4672 | 0.9390 |
0.4447 | 5.0 | 1590 | 0.3966 | 0.9426 |
0.4447 | 6.0 | 1908 | 0.3701 | 0.9458 |
0.2865 | 7.0 | 2226 | 0.3595 | 0.9452 |
0.24 | 8.0 | 2544 | 0.3475 | 0.9490 |
0.24 | 9.0 | 2862 | 0.3453 | 0.9494 |
0.2199 | 10.0 | 3180 | 0.3448 | 0.9497 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 10
Finetuned from
Dataset used to train dodiaz2111/distilbert-base-uncased-distilled-clinc
Evaluation results
- Accuracy on clinc_oosvalidation set self-reported0.950