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: 0.1259
- Accuracy: 0.9332
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: 7
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 318 | 0.5952 | 0.7355 |
0.7663 | 2.0 | 636 | 0.3130 | 0.8742 |
0.7663 | 3.0 | 954 | 0.2024 | 0.9206 |
0.3043 | 4.0 | 1272 | 0.1590 | 0.9235 |
0.181 | 5.0 | 1590 | 0.1378 | 0.9303 |
0.181 | 6.0 | 1908 | 0.1287 | 0.9329 |
0.1468 | 7.0 | 2226 | 0.1259 | 0.9332 |
Framework versions
- Transformers 4.16.2
- Pytorch 1.10.2+cu102
- Datasets 1.18.3
- Tokenizers 0.11.0
- Downloads last month
- 24
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Dataset used to train Omar95farag/distilbert-base-uncased-distilled-clinc
Evaluation results
- Accuracy on clinc_oosself-reported0.933
- Accuracy on clinc_oostest set self-reported0.859
- Precision Macro on clinc_oostest set self-reported0.862
- Precision Micro on clinc_oostest set self-reported0.859
- Precision Weighted on clinc_oostest set self-reported0.880
- Recall Macro on clinc_oostest set self-reported0.936
- Recall Micro on clinc_oostest set self-reported0.859
- Recall Weighted on clinc_oostest set self-reported0.859
- F1 Macro on clinc_oostest set self-reported0.892
- F1 Micro on clinc_oostest set self-reported0.859