metadata

license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner-cadec
    results: []

bert-finetuned-ner-cadec

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: 0.2334
Precision: 0.6055
Recall: 0.6988
F1: 0.6488
Accuracy: 0.9250
Adr Precision: 0.5685
Adr Recall: 0.6992
Adr F1: 0.6271
Disease Precision: 0.25
Disease Recall: 0.125
Disease F1: 0.1667
Drug Precision: 0.8371
Drug Recall: 0.9069
Drug F1: 0.8706
Finding Precision: 0.2439
Finding Recall: 0.3448
Finding F1: 0.2857
Symptom Precision: 0.5
Symptom Recall: 0.0870
Symptom F1: 0.1481
B-adr Precision: 0.7596
B-adr Recall: 0.8357
B-adr F1: 0.7958
B-disease Precision: 0.6
B-disease Recall: 0.1875
B-disease F1: 0.2857
B-drug Precision: 0.9423
B-drug Recall: 0.9655
B-drug F1: 0.9538
B-finding Precision: 0.5789
B-finding Recall: 0.3793
B-finding F1: 0.4583
B-symptom Precision: 0.5
B-symptom Recall: 0.0870
B-symptom F1: 0.1481
I-adr Precision: 0.5699
I-adr Recall: 0.6782
I-adr F1: 0.6194
I-disease Precision: 0.3333
I-disease Recall: 0.1379
I-disease F1: 0.1951
I-drug Precision: 0.8611
I-drug Recall: 0.9118
I-drug F1: 0.8857
I-finding Precision: 0.3125
I-finding Recall: 0.3704
I-finding F1: 0.3390
I-symptom Precision: 0.0
I-symptom Recall: 0.0
I-symptom F1: 0.0
Macro Avg F1: 0.4681
Weighted Avg F1: 0.7238

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy	Adr Precision	Adr Recall	Adr F1	Disease Precision	Disease Recall	Disease F1	Drug Precision	Drug Recall	Drug F1	Finding Precision	Finding Recall	Finding F1	Symptom Precision	Symptom Recall	Symptom F1	B-adr Precision	B-adr Recall	B-adr F1	B-disease Precision	B-disease Recall	B-disease F1	B-drug Precision	B-drug Recall	B-drug F1	B-finding Precision	B-finding Recall	B-finding F1	B-symptom Precision	B-symptom Recall	B-symptom F1	I-adr Precision	I-adr Recall	I-adr F1	I-disease Precision	I-disease Recall	I-disease F1	I-drug Precision	I-drug Recall	I-drug F1	I-finding Precision	I-finding Recall	I-finding F1	Macro Avg F1	Weighted Avg F1
No log	1.0	127	0.2633	0.5612	0.6348	0.5958	0.9139	0.5047	0.6436	0.5658	0.0	0.0	0.0	0.8148	0.8627	0.8381	0.0714	0.0345	0.0465	0.0	0.0	0.0	0.7530	0.7778	0.7652	0.0	0.0	0.0	0.9154	0.9064	0.9109	1.0	0.0690	0.1290	0.0	0.0	0.0	0.4993	0.6362	0.5595	0.0	0.0	0.0	0.8775	0.8775	0.8775	0.3077	0.1481	0.2	0.3442	0.6698
No log	2.0	254	0.2358	0.6	0.6863	0.6402	0.9240	0.5595	0.6857	0.6162	0.2222	0.125	0.16	0.8296	0.9069	0.8665	0.2647	0.3103	0.2857	0.0	0.0	0.0	0.7649	0.8247	0.7937	0.8333	0.1562	0.2632	0.9327	0.9557	0.9440	0.7222	0.4483	0.5532	0.0	0.0	0.0	0.5646	0.6709	0.6132	0.2222	0.1379	0.1702	0.8664	0.9216	0.8931	0.28	0.2593	0.2692	0.4500	0.7185
No log	3.0	381	0.2334	0.6055	0.6988	0.6488	0.9250	0.5685	0.6992	0.6271	0.25	0.125	0.1667	0.8371	0.9069	0.8706	0.2439	0.3448	0.2857	0.5	0.0870	0.1481	0.7596	0.8357	0.7958	0.6	0.1875	0.2857	0.9423	0.9655	0.9538	0.5789	0.3793	0.4583	0.5	0.0870	0.1481	0.5699	0.6782	0.6194	0.3333	0.1379	0.1951	0.8611	0.9118	0.8857	0.3125	0.3704	0.3390	0.4681	0.7238

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0