DeepNeural/medical-ner

Model Name: DeepNeural_NER-I

Bert-base-uncased

This model is a fine-tuned version of bert-base-uncased on the medical-ner-bleurt-separated dataset. It achieves the following results on the evaluation set:

• Loss: 0.0
• F1: 1.0

Model description

The DeepNeural NER-I model is exclusively designed to identify body parts in textual documents. This clinical support model is one of many to be released, and is a crucial aspect of clinical support systems.

Intended uses & limitations

The model is meant to be used for research and development purposes by Data Scientists, ML & Software Engineers for the development of NER applications capable of identifying body parts in medical EHR systems to augment patient health processing.

Training and evaluation data

Training

Training procedure

The DeepNeural_NER-I model was trained with precision and accuracy in mind, and therefore the model was trained for 3 epochs and 13500 global steps per epoch. The training scores utilized are highlighted in the table below.

Training Method	# Score
Precision	1.0
Recall	1.0
F1-Score	1.0
Accuracy	1.0

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 24
• eval_batch_size: 24
• lr_scheduler_type: linear
• num_epochs: 3
• weight_decay: 0.01

Training results

Training Loss	Epoch	Validation Loss	F1
2.61	1.0	0.0	1.0
2.61	2.0	0.0	1.0
2.61	3.0	0.0	1.0

Framework versions

• Transformers 4.56.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0