metadata
license: mit
base_model: emilyalsentzer/Bio_ClinicalBERT
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: BioClinicalBERT-full-finetuned-ner-pablo
results: []
BioClinicalBERT-full-finetuned-ner-pablo
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: 0.1136
- Precision: 0.8112
- Recall: 0.8083
- F1: 0.8098
- Accuracy: 0.9747
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.2583 | 0.9990 | 781 | 0.0983 | 0.7777 | 0.7768 | 0.7773 | 0.9721 |
| 0.0794 | 1.9994 | 1563 | 0.0944 | 0.7819 | 0.7879 | 0.7849 | 0.9736 |
| 0.0614 | 2.9997 | 2345 | 0.0913 | 0.7861 | 0.8018 | 0.7939 | 0.9733 |
| 0.0408 | 4.0 | 3127 | 0.1031 | 0.8007 | 0.8006 | 0.8006 | 0.9736 |
| 0.0298 | 4.9952 | 3905 | 0.1136 | 0.8112 | 0.8083 | 0.8098 | 0.9747 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0+cu124
- Datasets 2.21.0
- Tokenizers 0.19.1