Bio_ClinicalBERT-finetuned-medicalcondition
This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7201
- F1 Score: 0.8254
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | F1 Score |
---|---|---|---|---|
0.8002 | 1.0 | 1772 | 0.6327 | 0.7759 |
0.5933 | 2.0 | 3544 | 0.5906 | 0.7934 |
0.5015 | 3.0 | 5316 | 0.5768 | 0.8033 |
0.4265 | 4.0 | 7088 | 0.5792 | 0.8099 |
0.3698 | 5.0 | 8860 | 0.6030 | 0.8109 |
0.3229 | 6.0 | 10632 | 0.6366 | 0.8167 |
0.2907 | 7.0 | 12404 | 0.6671 | 0.8198 |
0.2649 | 8.0 | 14176 | 0.6850 | 0.8237 |
0.2477 | 9.0 | 15948 | 0.7072 | 0.8247 |
0.2348 | 10.0 | 17720 | 0.7201 | 0.8254 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2
- Downloads last month
- 83
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.