bc2gm_corpus-Bio_ClinicalBERT-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
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: 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
- Downloads last month
- 6
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.
Dataset used to train commanderstrife/bc2gm_corpus-Bio_ClinicalBERT-finetuned-ner
Evaluation results
- Precision on bc2gm_corpusself-reported0.785
- Recall on bc2gm_corpusself-reported0.816
- F1 on bc2gm_corpusself-reported0.800
- Accuracy on bc2gm_corpusself-reported0.976