distilbert-base-uncased-distilled-clinc
This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2862
- Accuracy: 0.9455
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 |
---|---|---|---|---|
No log | 1.0 | 318 | 2.4830 | 0.7252 |
2.8957 | 2.0 | 636 | 1.2862 | 0.8645 |
2.8957 | 3.0 | 954 | 0.7035 | 0.9116 |
1.1264 | 4.0 | 1272 | 0.4712 | 0.9303 |
0.4585 | 5.0 | 1590 | 0.3717 | 0.9403 |
0.4585 | 6.0 | 1908 | 0.3314 | 0.9429 |
0.2603 | 7.0 | 2226 | 0.3034 | 0.9452 |
0.1898 | 8.0 | 2544 | 0.2937 | 0.9432 |
0.1898 | 9.0 | 2862 | 0.2877 | 0.9458 |
0.1637 | 10.0 | 3180 | 0.2862 | 0.9455 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 4