metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-medical-ner
    results: []

bert-medical-ner

This model is a fine-tuned version of bert-base-cased on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.0409
Precision: 0.6097
Recall: 0.6323
F1: 0.6208
Accuracy: 0.7607

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	63	1.6300	0.3434	0.3838	0.3625	0.6077
No log	2.0	126	1.2289	0.4831	0.5207	0.5012	0.6893
No log	3.0	189	1.0878	0.5261	0.5762	0.5500	0.7197
No log	4.0	252	1.0253	0.5541	0.5914	0.5721	0.7328
No log	5.0	315	0.9738	0.5689	0.6040	0.5859	0.7416
No log	6.0	378	0.9498	0.5828	0.6094	0.5958	0.7472
No log	7.0	441	0.9532	0.5954	0.6126	0.6039	0.7509
1.1083	8.0	504	0.9515	0.5994	0.6166	0.6079	0.7530
1.1083	9.0	567	0.9572	0.6010	0.6212	0.6109	0.7547
1.1083	10.0	630	0.9690	0.5986	0.6162	0.6072	0.7539
1.1083	11.0	693	0.9798	0.5953	0.6232	0.6089	0.7532
1.1083	12.0	756	0.9813	0.5986	0.6185	0.6084	0.7546
1.1083	13.0	819	0.9984	0.5979	0.6182	0.6079	0.7539
1.1083	14.0	882	1.0111	0.6026	0.6226	0.6124	0.7557
1.1083	15.0	945	1.0140	0.6050	0.6262	0.6155	0.7572
0.4329	16.0	1008	1.0252	0.6112	0.6210	0.6160	0.7580
0.4329	17.0	1071	1.0312	0.6090	0.6288	0.6187	0.7602
0.4329	18.0	1134	1.0368	0.6059	0.6314	0.6184	0.7597
0.4329	19.0	1197	1.0395	0.6095	0.6299	0.6196	0.7599
0.4329	20.0	1260	1.0409	0.6097	0.6323	0.6208	0.7607

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3