bert-finetuned-ner / README.md
csariyildiz's picture
Update README.md
d67a90d
metadata
license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner4
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: validation
          args: conll2003
        metrics:
          - name: Precision
            type: precision
            value: 0.9264802631578948
          - name: Recall
            type: recall
            value: 0.947997307303938
          - name: F1
            type: f1
            value: 0.9371152886374979
          - name: Accuracy
            type: accuracy
            value: 0.9859304173779949

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