bert-base-CONTINUE-finetuned-ner-chim-v1

• Loss: 1.1510
• Accuracy: 0.7001
• Precision: 0.1800
• Recall: 0.2172
• F1: 0.1819
• Date Precision: 0.4783
• Date Recall: 0.275
• Date F1-score: 0.3492
• Habitat Precision: 0.0
• Habitat Recall: 0.0
• Habitat F1-score: 0.0
• Id Feature Precision: 0.0379
• Id Feature Recall: 0.0909
• Id Feature F1-score: 0.0535
• Location Precision: 0.1982
• Location Recall: 0.4718
• Location F1-score: 0.2792
• Organization Precision: 0.0
• Organization Recall: 0.0
• Organization F1-score: 0.0
• Species Precision: 0.3656
• Species Recall: 0.4658
• Species F1-score: 0.4096
• Micro avg Precision: 0.2352
• Micro avg Recall: 0.3075
• Micro avg F1-score: 0.2665
• Macro avg Precision: 0.1800
• Macro avg Recall: 0.2172
• Macro avg F1-score: 0.1819
• Weighted avg Precision: 0.2180
• Weighted avg Recall: 0.3075
• Weighted avg F1-score: 0.2464

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1