bert-finetuned-ner

This model is a fine-tuned version of bert-base-cased on the conll2003 dataset. It achieves the following results on the evaluation set:

• Loss: 0.0741
• Precision: 0.9341
• Recall: 0.9520
• F1: 0.9430
• Accuracy: 0.9867

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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0775	1.0	1756	0.0694	0.8912	0.9273	0.9089	0.9817
0.0377	2.0	3512	0.0707	0.9245	0.9445	0.9344	0.9850
0.0243	3.0	5268	0.0671	0.9281	0.9465	0.9372	0.9855
0.0145	4.0	7024	0.0734	0.9353	0.9507	0.9429	0.9859
0.006	5.0	8780	0.0741	0.9341	0.9520	0.9430	0.9867

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1

How to use and it's democase

from transformers import pipeline

model_checkpoint = "amannagrawall002/bert-finetuned-ner" token_classifier = pipeline( "token-classification", model=model_checkpoint, aggregation_strategy="simple" )

print(token_classifier("My name is Sylvain and I work at Hugging Face in Brooklyn."))

[{'entity_group': 'PER', 'score': 0.9997023, 'word': 'Sylvain', 'start': 11, 'end': 18}, {'entity_group': 'ORG', 'score': 0.995275, 'word': 'Hugging Face', 'start': 33, 'end': 45}, {'entity_group': 'LOC', 'score': 0.9987465, 'word': 'Brooklyn', 'start': 49, 'end': 57}]