<!-- 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. -->
08-3-4-distilbert-base-uncased-finetuned-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: 0.7777
- Accuracy: 0.9152
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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
No log | 1.0 | 318 | 3.3018 | 0.7439 |
3.7971 | 2.0 | 636 | 1.8880 | 0.8406 |
3.7971 | 3.0 | 954 | 1.1649 | 0.8932 |
1.7002 | 4.0 | 1272 | 0.8611 | 0.9119 |
0.9041 | 5.0 | 1590 | 0.7777 | 0.9152 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1
- Datasets 2.8.0
- Tokenizers 0.13.2