legal-bert-base-NER

This model is a fine-tuned version of nlpaueb/legal-bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0011

• Accuracy: 0.9998

• Precision: 0.9992

• Recall: 0.9988

• F1: 0.9990

• Classification Report: precision recall f1-score support

     LOC       1.00      1.00      1.00      1837
    MISC       1.00      1.00      1.00       922
     ORG       1.00      1.00      1.00      1341
     PER       1.00      1.00      1.00      1842
  

  micro avg 1.00 1.00 1.00 5942 macro avg 1.00 1.00 1.00 5942

weighted avg 1.00 1.00 1.00 5942

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: 5e-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: 5

Training results

     LOC       0.99      0.99      0.99      1837
    MISC       0.98      0.97      0.98       922
     ORG       0.98      0.99      0.99      1341
     PER       1.00      1.00      1.00      1842

micro avg 0.99 0.99 0.99 5942 macro avg 0.99 0.99 0.99 5942 weighted avg 0.99 0.99 0.99 5942 | | 0.0043 | 4.61 | 1000 | 0.0011 | 0.9998 | 0.9992 | 0.9988 | 0.9990 | precision recall f1-score support

     LOC       1.00      1.00      1.00      1837
    MISC       1.00      1.00      1.00       922
     ORG       1.00      1.00      1.00      1341
     PER       1.00      1.00      1.00      1842

micro avg 1.00 1.00 1.00 5942 macro avg 1.00 1.00 1.00 5942 weighted avg 1.00 1.00 1.00 5942 |

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3