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: 0.4966
Precision: 0.7640
Recall: 0.6936
F1: 0.7271
Accuracy: 0.9433

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	0.4909	0.8023	0.6653	0.7274	0.9429
No log	2.0	126	0.4686	0.7434	0.6829	0.7118	0.9414
No log	3.0	189	0.4578	0.6967	0.6987	0.6977	0.9378
No log	4.0	252	0.4689	0.7492	0.6942	0.7207	0.9425
No log	5.0	315	0.4882	0.7613	0.6744	0.7152	0.9412
No log	6.0	378	0.4880	0.7417	0.6914	0.7156	0.9403
No log	7.0	441	0.4823	0.7448	0.7027	0.7231	0.9419
0.0036	8.0	504	0.4787	0.7318	0.7049	0.7181	0.9399
0.0036	9.0	567	0.4953	0.7413	0.6981	0.7191	0.9425
0.0036	10.0	630	0.4910	0.7442	0.7038	0.7234	0.9426
0.0036	11.0	693	0.4894	0.7421	0.7044	0.7227	0.9411
0.0036	12.0	756	0.4958	0.7402	0.7072	0.7233	0.9408
0.0036	13.0	819	0.5032	0.7438	0.6976	0.7200	0.9416
0.0036	14.0	882	0.5009	0.7241	0.7060	0.7149	0.9396
0.0036	15.0	945	0.5033	0.7653	0.6947	0.7283	0.9432
0.0018	16.0	1008	0.5101	0.7814	0.6829	0.7288	0.9434
0.0018	17.0	1071	0.4935	0.7606	0.6987	0.7283	0.9440
0.0018	18.0	1134	0.4920	0.7549	0.7015	0.7272	0.9433
0.0018	19.0	1197	0.4970	0.7613	0.6959	0.7271	0.9434
0.0018	20.0	1260	0.4966	0.7640	0.6936	0.7271	0.9433

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3