<!-- 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-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: 0.1123
- Accuracy: 0.94
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 |
---|---|---|---|---|
1.0212 | 1.0 | 318 | 0.6302 | 0.7303 |
0.4836 | 2.0 | 636 | 0.2955 | 0.8765 |
0.2603 | 3.0 | 954 | 0.1814 | 0.9184 |
0.1795 | 4.0 | 1272 | 0.1439 | 0.9294 |
0.1464 | 5.0 | 1590 | 0.1294 | 0.9348 |
0.1312 | 6.0 | 1908 | 0.1213 | 0.94 |
0.1218 | 7.0 | 2226 | 0.1171 | 0.9390 |
0.1163 | 8.0 | 2544 | 0.1144 | 0.9403 |
0.113 | 9.0 | 2862 | 0.1128 | 0.94 |
0.1118 | 10.0 | 3180 | 0.1123 | 0.94 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2