Symptoms_to_Diagnosis_SonatafyAI_BERT_v1
This model is a fine-tuned version of bert-base-uncased on the symptoms to diagnosis dataset. It achieves the following results on the evaluation set:
- Loss: 0.4088
- Accuracy: 0.9387
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: 16
- eval_batch_size: 16
- 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 | 54 | 2.7055 | 0.25 |
| No log | 2.0 | 108 | 2.1468 | 0.6792 |
| No log | 3.0 | 162 | 1.5608 | 0.8019 |
| No log | 4.0 | 216 | 1.1596 | 0.8632 |
| No log | 5.0 | 270 | 0.8834 | 0.8868 |
| No log | 6.0 | 324 | 0.6775 | 0.9104 |
| No log | 7.0 | 378 | 0.5516 | 0.9198 |
| No log | 8.0 | 432 | 0.4632 | 0.9434 |
| No log | 9.0 | 486 | 0.4273 | 0.9387 |
| 1.2941 | 10.0 | 540 | 0.4088 | 0.9387 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2