bert-finetuned-ner

• Loss: 0.2651
• Entity Metrics: {'O': {'precision': 1.0, 'recall': 1.0, 'f1': 1.0}, 'B-ADR': {'precision': 0.9613259668508287, 'recall': 1.0, 'f1': 0.9802816901408451}, 'I-ADR': {'precision': 0.9608938547486033, 'recall': 0.9942196531791907, 'f1': 0.9772727272727273}, 'B-Disease': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0}, 'I-Disease': {'precision': 0.5294117647058824, 'recall': 0.2903225806451613, 'f1': 0.375}, 'B-Drug': {'precision': 0.9910714285714286, 'recall': 0.9910714285714286, 'f1': 0.9910714285714286}, 'I-Drug': {'precision': 1.0, 'recall': 0.9910714285714286, 'f1': 0.9955156950672646}, 'B-Finding': {'precision': 0.6190476190476191, 'recall': 0.28888888888888886, 'f1': 0.3939393939393939}, 'I-Finding': {'precision': 0.41935483870967744, 'recall': 0.325, 'f1': 0.36619718309859156}, 'B-Symptom': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0}, 'I-Symptom': {'precision': 0.0, 'recall': 0.0, 'f1': 0.0}}
• Macro F1: 0.5527
• Micro F1: 0.9162

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• 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