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: 1.0001
Precision: 0.6207
Recall: 0.6501
F1: 0.6351
Accuracy: 0.7695

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	1.5798	0.3498	0.3921	0.3697	0.6168
No log	2.0	126	1.1942	0.5020	0.5286	0.5150	0.7028
No log	3.0	189	1.0593	0.5345	0.5826	0.5575	0.7280
No log	4.0	252	0.9799	0.5722	0.6065	0.5889	0.7451
No log	5.0	315	0.9394	0.5905	0.6187	0.6043	0.7534
No log	6.0	378	0.9171	0.5995	0.6262	0.6126	0.7576
No log	7.0	441	0.9068	0.6071	0.6324	0.6195	0.7623
1.0968	8.0	504	0.9076	0.6171	0.6323	0.6246	0.7638
1.0968	9.0	567	0.9280	0.6095	0.6361	0.6225	0.7637
1.0968	10.0	630	0.9231	0.6117	0.6414	0.6262	0.7670
1.0968	11.0	693	0.9322	0.6183	0.6460	0.6319	0.7685
1.0968	12.0	756	0.9529	0.6200	0.6503	0.6347	0.7689
1.0968	13.0	819	0.9550	0.6148	0.6451	0.6296	0.7672
1.0968	14.0	882	0.9736	0.6227	0.6466	0.6344	0.7688
1.0968	15.0	945	0.9791	0.6206	0.6460	0.6330	0.7679
0.4223	16.0	1008	0.9854	0.6194	0.6490	0.6339	0.7699
0.4223	17.0	1071	0.9870	0.6185	0.6494	0.6336	0.7692
0.4223	18.0	1134	0.9957	0.6208	0.6498	0.6350	0.7702
0.4223	19.0	1197	0.9994	0.6189	0.6510	0.6345	0.7693
0.4223	20.0	1260	1.0001	0.6207	0.6501	0.6351	0.7695

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu117
Datasets 2.12.0
Tokenizers 0.13.3