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: 0.3091
- Accuracy: 0.9442
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 |
---|---|---|---|---|
2.6639 | 1.0 | 318 | 1.9373 | 0.7223 |
1.5046 | 2.0 | 636 | 0.9952 | 0.8616 |
0.7975 | 3.0 | 954 | 0.5725 | 0.9139 |
0.4764 | 4.0 | 1272 | 0.4208 | 0.9297 |
0.3412 | 5.0 | 1590 | 0.3575 | 0.9387 |
0.2834 | 6.0 | 1908 | 0.3326 | 0.9423 |
0.2533 | 7.0 | 2226 | 0.3210 | 0.9423 |
0.2381 | 8.0 | 2544 | 0.3159 | 0.9423 |
0.23 | 9.0 | 2862 | 0.3107 | 0.9432 |
0.2254 | 10.0 | 3180 | 0.3091 | 0.9442 |
Framework versions
- Transformers 4.36.1
- Pytorch 2.1.2+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 0
Finetuned from
Dataset used to train balus/distilbert-base-uncased-distilled-clinc
Evaluation results
- Accuracy on clinc_oosvalidation set self-reported0.944