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: 0.2301
- Precision: 0.5948
- Recall: 0.6779
- F1: 0.6336
- Accuracy: 0.9265
- Adr Precision: 0.5579
- Adr Recall: 0.6812
- Adr F1: 0.6134
- Disease Precision: 0.2273
- Disease Recall: 0.1562
- Disease F1: 0.1852
- Drug Precision: 0.8136
- Drug Recall: 0.8775
- Drug F1: 0.8443
- Finding Precision: 0.2667
- Finding Recall: 0.2759
- Finding F1: 0.2712
- Symptom Precision: 0.5
- Symptom Recall: 0.0435
- Symptom F1: 0.08
- B-adr Precision: 0.7749
- B-adr Recall: 0.8513
- B-adr F1: 0.8113
- B-disease Precision: 1.0
- B-disease Recall: 0.1562
- B-disease F1: 0.2703
- B-drug Precision: 0.9327
- B-drug Recall: 0.9557
- B-drug F1: 0.9440
- B-finding Precision: 0.5909
- B-finding Recall: 0.4483
- B-finding F1: 0.5098
- B-symptom Precision: 0.5
- B-symptom Recall: 0.0435
- B-symptom F1: 0.08
- I-adr Precision: 0.5725
- I-adr Recall: 0.6782
- I-adr F1: 0.6209
- I-disease Precision: 0.4091
- I-disease Recall: 0.3103
- I-disease F1: 0.3529
- I-drug Precision: 0.8458
- I-drug Recall: 0.8873
- I-drug F1: 0.8660
- I-finding Precision: 0.3529
- I-finding Recall: 0.2222
- I-finding F1: 0.2727
- I-symptom Precision: 0.0
- I-symptom Recall: 0.0
- I-symptom F1: 0.0
- Macro Avg F1: 0.4728
- Weighted Avg F1: 0.7278
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 | I-symptom Precision | I-symptom Recall | I-symptom F1 | Macro Avg F1 | Weighted Avg F1 |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
No log | 1.0 | 127 | 0.2653 | 0.5472 | 0.6201 | 0.5814 | 0.9128 | 0.4942 | 0.6376 | 0.5568 | 0.0 | 0.0 | 0.0 | 0.7952 | 0.8186 | 0.8068 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.7530 | 0.7731 | 0.7629 | 0.0 | 0.0 | 0.0 | 0.9179 | 0.8818 | 0.8995 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.0 | 0.4915 | 0.6325 | 0.5532 | 0.1429 | 0.0345 | 0.0556 | 0.855 | 0.8382 | 0.8465 | 0.3333 | 0.0370 | 0.0667 | 0.0 | 0.0 | 0.0 | 0.3184 | 0.6587 |
No log | 2.0 | 254 | 0.2307 | 0.5896 | 0.6632 | 0.6242 | 0.9254 | 0.5546 | 0.6722 | 0.6077 | 0.2222 | 0.1875 | 0.2034 | 0.8093 | 0.8529 | 0.8305 | 0.2083 | 0.1724 | 0.1887 | 0.0 | 0.0 | 0.0 | 0.7663 | 0.8263 | 0.7952 | 1.0 | 0.1562 | 0.2703 | 0.9366 | 0.9458 | 0.9412 | 0.625 | 0.3448 | 0.4444 | 0.0 | 0.0 | 0.0 | 0.5649 | 0.6600 | 0.6088 | 0.2963 | 0.2759 | 0.2857 | 0.8495 | 0.8578 | 0.8537 | 0.3846 | 0.1852 | 0.25 | 0.0 | 0.0 | 0.0 | 0.4449 | 0.7127 |
No log | 3.0 | 381 | 0.2301 | 0.5948 | 0.6779 | 0.6336 | 0.9265 | 0.5579 | 0.6812 | 0.6134 | 0.2273 | 0.1562 | 0.1852 | 0.8136 | 0.8775 | 0.8443 | 0.2667 | 0.2759 | 0.2712 | 0.5 | 0.0435 | 0.08 | 0.7749 | 0.8513 | 0.8113 | 1.0 | 0.1562 | 0.2703 | 0.9327 | 0.9557 | 0.9440 | 0.5909 | 0.4483 | 0.5098 | 0.5 | 0.0435 | 0.08 | 0.5725 | 0.6782 | 0.6209 | 0.4091 | 0.3103 | 0.3529 | 0.8458 | 0.8873 | 0.8660 | 0.3529 | 0.2222 | 0.2727 | 0.0 | 0.0 | 0.0 | 0.4728 | 0.7278 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 24
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.
Model tree for mireiaplalis/bert-finetuned-ner-cadec
Base model
google-bert/bert-base-cased