clinical-miniALBERT-312-medical-text-classification
This model is a fine-tuned version of nlpie/clinical-miniALBERT-312 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.3237
- Accuracy: 0.186
- Precision: 0.1659
- Recall: 0.186
- F1: 0.1736
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: 5e-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
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 2.8556 | 1.0 | 250 | 2.9403 | 0.221 | 0.0488 | 0.221 | 0.0800 |
| 2.3771 | 2.0 | 500 | 2.6223 | 0.324 | 0.1226 | 0.324 | 0.1772 |
| 2.4809 | 3.0 | 750 | 2.4574 | 0.365 | 0.1918 | 0.365 | 0.2409 |
| 2.3648 | 4.0 | 1000 | 2.4098 | 0.34 | 0.1762 | 0.34 | 0.2241 |
| 2.1697 | 5.0 | 1250 | 2.4202 | 0.346 | 0.2038 | 0.346 | 0.2457 |
| 2.0393 | 6.0 | 1500 | 2.3783 | 0.333 | 0.2220 | 0.333 | 0.2564 |
| 1.8836 | 7.0 | 1750 | 2.3133 | 0.279 | 0.2113 | 0.279 | 0.2289 |
| 1.6791 | 8.0 | 2000 | 2.2241 | 0.256 | 0.2115 | 0.256 | 0.2260 |
| 1.6044 | 9.0 | 2250 | 2.2828 | 0.235 | 0.1965 | 0.235 | 0.2055 |
| 1.4025 | 10.0 | 2500 | 2.3237 | 0.186 | 0.1659 | 0.186 | 0.1736 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2