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: 0.3538
- Accuracy: 0.9445
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 | 2.6372 | 0.7235 |
3.0882 | 2.0 | 636 | 1.3409 | 0.8648 |
3.0882 | 3.0 | 954 | 0.7276 | 0.91 |
1.1765 | 4.0 | 1272 | 0.4936 | 0.9335 |
0.4733 | 5.0 | 1590 | 0.4103 | 0.9387 |
0.4733 | 6.0 | 1908 | 0.3827 | 0.9406 |
0.2919 | 7.0 | 2226 | 0.3657 | 0.9423 |
0.2358 | 8.0 | 2544 | 0.3587 | 0.9442 |
0.2358 | 9.0 | 2862 | 0.3555 | 0.9435 |
0.2158 | 10.0 | 3180 | 0.3538 | 0.9445 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 2