bert-finetuned-ner4

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: 0.0599
• Precision: 0.9265
• Recall: 0.9480
• F1: 0.9371
• Accuracy: 0.9859

Usage

from transformers import pipeline
import json

model_checkpoint = "./bert-finetuned-ner4"
token_classifier = pipeline(
    "token-classification", model=model_checkpoint, aggregation_strategy="simple"
)

with open('./assets/test2.json', 'r') as json_file:
    data = json.load(json_file)

for item in data:
    print(item)
    print(token_classifier(item)) 

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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0765	1.0	1756	0.0752	0.9082	0.9344	0.9211	0.9795
0.0432	2.0	3512	0.0577	0.9257	0.9480	0.9367	0.9859
0.0243	3.0	5268	0.0599	0.9265	0.9480	0.9371	0.9859

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1