<!-- 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: 0.3032
- Accuracy: 0.9490
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 |
---|---|---|---|---|
2.6314 | 1.0 | 318 | 1.8942 | 0.7274 |
1.4611 | 2.0 | 636 | 0.9553 | 0.8594 |
0.7635 | 3.0 | 954 | 0.5469 | 0.9181 |
0.4613 | 4.0 | 1272 | 0.4035 | 0.9394 |
0.3348 | 5.0 | 1590 | 0.3505 | 0.9432 |
0.2776 | 6.0 | 1908 | 0.3258 | 0.9445 |
0.2509 | 7.0 | 2226 | 0.3148 | 0.9455 |
0.236 | 8.0 | 2544 | 0.3066 | 0.9494 |
0.2282 | 9.0 | 2862 | 0.3055 | 0.9484 |
0.224 | 10.0 | 3180 | 0.3032 | 0.9490 |
Framework versions
- Transformers 4.33.1
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2