bert-finetuned-ner-bilstm

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

bert-finetuned-ner-bilstm

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: 0.2441
• Entity Metrics: {'O': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'B-ADR': {'precision': 0.9516129032258065, 'recall': 0.9888268156424581, 'f1': 0.9698630136986301}, 'I-ADR': {'precision': 0.9411764705882353, 'recall': 0.9943502824858758, 'f1': 0.9670329670329672}, 'B-Disease': {'precision': 0.5882352941176471, 'recall': 0.3225806451612903, 'f1': 0.41666666666666663}, 'I-Disease': {'precision': 0.5, 'recall': 0.4482758620689655, 'f1': 0.4727272727272727}, 'B-Drug': {'precision': 0.9836065573770492, 'recall': 0.975609756097561, 'f1': 0.9795918367346939}, 'I-Drug': {'precision': 0.991869918699187, 'recall': 0.991869918699187, 'f1': 0.991869918699187}, 'B-Finding': {'precision': 0.875, 'recall': 0.19444444444444445, 'f1': 0.3181818181818182}, 'I-Finding': {'precision': 0.7368421052631579, 'recall': 0.4117647058823529, 'f1': 0.5283018867924528}, 'B-Symptom': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0}, 'I-Symptom': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0}}
• Macro F1: 0.6040
• Micro F1: 0.9196

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

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cpu
• Datasets 2.16.0
• Tokenizers 0.15.0