NER-finetuning-BERT-uncased-actual

This model is a fine-tuned version of google-bert/bert-base-uncased on the conll2002 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1792
• Precision: 0.7223
• Recall: 0.7675
• F1: 0.7442
• Accuracy: 0.9551

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: 4
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1581	1.0	2081	0.1857	0.6602	0.7004	0.6797	0.9461
0.0874	2.0	4162	0.1792	0.7223	0.7675	0.7442	0.9551

Framework versions

• Transformers 4.51.2
• Pytorch 2.6.0+cu126
• Datasets 3.5.0
• Tokenizers 0.21.1