distilbert-base-uncased-finetuned-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: 0.2509
- Accuracy: 0.9455
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 | 3.1887 | 0.7365 |
3.7205 | 2.0 | 636 | 1.5819 | 0.8697 |
3.7205 | 3.0 | 954 | 0.7941 | 0.9094 |
1.3585 | 4.0 | 1272 | 0.4804 | 0.9261 |
0.4416 | 5.0 | 1590 | 0.3437 | 0.9371 |
0.4416 | 6.0 | 1908 | 0.2871 | 0.9465 |
0.1815 | 7.0 | 2226 | 0.2657 | 0.9458 |
0.0931 | 8.0 | 2544 | 0.2588 | 0.9461 |
0.0931 | 9.0 | 2862 | 0.2524 | 0.9458 |
0.0618 | 10.0 | 3180 | 0.2509 | 0.9455 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0
- Downloads last month
- 0
Finetuned from
Dataset used to train iamsubrata/distilbert-base-uncased-finetuned-clinc
Evaluation results
- Accuracy on clinc_oosvalidation set self-reported0.945