Modelpublic

commanderstrife/bc2gm_corpus-Bio_ClinicalBERT-finetuned-ner

sourceHugging Facemitupdated 4y agoView on Hugging Face

0likes16downloads

Model Card

bc2gmcorpus-BioClinicalBERT-finetuned-ner

This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the bc2gm_corpus dataset. It achieves the following results on the evaluation set:

—Loss: 0.1505
—Precision: 0.7854
—Recall: 0.8158
—F1: 0.8003
—Accuracy: 0.9759

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
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0981	1.0	782	0.0712	0.7228	0.7948	0.7571	0.9724
0.0509	2.0	1564	0.0687	0.7472	0.8199	0.7818	0.9746
0.0121	3.0	2346	0.0740	0.7725	0.8011	0.7866	0.9747
0.0001	4.0	3128	0.1009	0.7618	0.8251	0.7922	0.9741
0.0042	5.0	3910	0.1106	0.7757	0.8185	0.7965	0.9754
0.0015	6.0	4692	0.1182	0.7812	0.8111	0.7958	0.9758
0.0001	7.0	5474	0.1283	0.7693	0.8275	0.7973	0.9753
0.0072	8.0	6256	0.1376	0.7863	0.8158	0.8008	0.9762
0.0045	9.0	7038	0.1468	0.7856	0.8180	0.8015	0.9761
0.0	10.0	7820	0.1505	0.7854	0.8158	0.8003	0.9759

Framework versions

—Transformers 4.20.1
—Pytorch 1.12.0+cu113
—Datasets 2.3.2
—Tokenizers 0.12.1