nominal-groups-recognition-medical-disease-competencia2-bert-medical-ner
This model is a fine-tuned version of ukkendane/bert-medical-ner on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3607
- Body Part Precision: 0.6555
- Body Part Recall: 0.7094
- Body Part F1: 0.6814
- Body Part Number: 413
- Disease Precision: 0.6835
- Disease Recall: 0.7067
- Disease F1: 0.6949
- Disease Number: 975
- Family Member Precision: 1.0
- Family Member Recall: 0.6
- Family Member F1: 0.7500
- Family Member Number: 30
- Medication Precision: 0.7647
- Medication Recall: 0.6989
- Medication F1: 0.7303
- Medication Number: 93
- Procedure Precision: 0.5385
- Procedure Recall: 0.5402
- Procedure F1: 0.5393
- Procedure Number: 311
- Overall Precision: 0.6594
- Overall Recall: 0.6767
- Overall F1: 0.6679
- Overall Accuracy: 0.9079
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: 13
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Body Part Precision | Body Part Recall | Body Part F1 | Body Part Number | Disease Precision | Disease Recall | Disease F1 | Disease Number | Family Member Precision | Family Member Recall | Family Member F1 | Family Member Number | Medication Precision | Medication Recall | Medication F1 | Medication Number | Procedure Precision | Procedure Recall | Procedure F1 | Procedure Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.4541 | 1.0 | 8025 | 0.3607 | 0.6555 | 0.7094 | 0.6814 | 413 | 0.6835 | 0.7067 | 0.6949 | 975 | 1.0 | 0.6 | 0.7500 | 30 | 0.7647 | 0.6989 | 0.7303 | 93 | 0.5385 | 0.5402 | 0.5393 | 311 | 0.6594 | 0.6767 | 0.6679 | 0.9079 |
0.3149 | 2.0 | 16050 | 0.3607 | 0.6555 | 0.7094 | 0.6814 | 413 | 0.6835 | 0.7067 | 0.6949 | 975 | 1.0 | 0.6 | 0.7500 | 30 | 0.7647 | 0.6989 | 0.7303 | 93 | 0.5385 | 0.5402 | 0.5393 | 311 | 0.6594 | 0.6767 | 0.6679 | 0.9079 |
0.3161 | 3.0 | 24075 | 0.3607 | 0.6555 | 0.7094 | 0.6814 | 413 | 0.6835 | 0.7067 | 0.6949 | 975 | 1.0 | 0.6 | 0.7500 | 30 | 0.7647 | 0.6989 | 0.7303 | 93 | 0.5385 | 0.5402 | 0.5393 | 311 | 0.6594 | 0.6767 | 0.6679 | 0.9079 |
0.3181 | 4.0 | 32100 | 0.3607 | 0.6555 | 0.7094 | 0.6814 | 413 | 0.6835 | 0.7067 | 0.6949 | 975 | 1.0 | 0.6 | 0.7500 | 30 | 0.7647 | 0.6989 | 0.7303 | 93 | 0.5385 | 0.5402 | 0.5393 | 311 | 0.6594 | 0.6767 | 0.6679 | 0.9079 |
0.3164 | 5.0 | 40125 | 0.3607 | 0.6555 | 0.7094 | 0.6814 | 413 | 0.6835 | 0.7067 | 0.6949 | 975 | 1.0 | 0.6 | 0.7500 | 30 | 0.7647 | 0.6989 | 0.7303 | 93 | 0.5385 | 0.5402 | 0.5393 | 311 | 0.6594 | 0.6767 | 0.6679 | 0.9079 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
- Downloads last month
- 140
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.