azizbarank's picture
update model card README.md
fbba54b
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wikiann
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: mbert-finetuned-azerbaijani-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: wikiann
          type: wikiann
          args: az
        metrics:
          - name: Precision
            type: precision
            value: 0.8898541731306236
          - name: Recall
            type: recall
            value: 0.915416533673795
          - name: F1
            type: f1
            value: 0.9024543738200126
          - name: Accuracy
            type: accuracy
            value: 0.966948310139165

mbert-finetuned-azerbaijani-ner

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

  • Loss: 0.1385
  • Precision: 0.8899
  • Recall: 0.9154
  • F1: 0.9025
  • Accuracy: 0.9669

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: 16
  • eval_batch_size: 16
  • 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
0.2928 1.0 625 0.1415 0.8584 0.8918 0.8748 0.9595
0.1254 2.0 1250 0.1335 0.8875 0.9119 0.8996 0.9637
0.077 3.0 1875 0.1385 0.8899 0.9154 0.9025 0.9669

Framework versions

  • Transformers 4.16.2
  • Pytorch 1.10.0+cu111
  • Datasets 1.18.3
  • Tokenizers 0.11.6