<!-- 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-finetuned-clinc
This model is a fine-tuned version of patnelt60/distilbert-base-uncased-finetuned-clinc on the clinc_oos dataset. It achieves the following results on the evaluation set:
- Loss: 0.1904
- Accuracy: 0.9268
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: 384
- eval_batch_size: 384
- 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 | 40 | 0.4572 | 0.8619 |
| No log | 2.0 | 80 | 0.3775 | 0.8881 |
| No log | 3.0 | 120 | 0.3184 | 0.9013 |
| No log | 4.0 | 160 | 0.2753 | 0.9110 |
| No log | 5.0 | 200 | 0.2441 | 0.9187 |
| No log | 6.0 | 240 | 0.2224 | 0.9232 |
| No log | 7.0 | 280 | 0.2073 | 0.9248 |
| 0.3426 | 8.0 | 320 | 0.1982 | 0.9268 |
| 0.3426 | 9.0 | 360 | 0.1923 | 0.9265 |
| 0.3426 | 10.0 | 400 | 0.1904 | 0.9268 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0
- Datasets 2.14.6
- Tokenizers 0.13.3
