peteryushunli's picture
Training complete
55cf6cb
|
raw
history blame
2.26 kB
metadata
license: apache-2.0
base_model: bert-base-cased
tags:
  - generated_from_trainer
datasets:
  - hausa_voa_ner
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-hausa_ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: hausa_voa_ner
          type: hausa_voa_ner
          config: hausa_voa_ner
          split: validation
          args: hausa_voa_ner
        metrics:
          - name: Precision
            type: precision
            value: 0.6781609195402298
          - name: Recall
            type: recall
            value: 0.7763157894736842
          - name: F1
            type: f1
            value: 0.7239263803680982
          - name: Accuracy
            type: accuracy
            value: 0.9516353514265832

bert-finetuned-hausa_ner

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

  • Loss: 0.1734
  • Precision: 0.6782
  • Recall: 0.7763
  • F1: 0.7239
  • Accuracy: 0.9516

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
No log 1.0 127 0.2162 0.6992 0.7342 0.7163 0.9516
No log 2.0 254 0.1702 0.6900 0.7789 0.7318 0.9518
No log 3.0 381 0.1734 0.6782 0.7763 0.7239 0.9516

Framework versions

  • Transformers 4.32.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3