TiffanyTiffany's picture
trainind complete
b414a28
metadata
license: cc-by-nc-sa-4.0
base_model: Babelscape/wikineural-multilingual-ner
tags:
  - generated_from_trainer
datasets:
  - wnut_17
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: bert-finetuned-ner-Colab
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: wnut_17
          type: wnut_17
          config: wnut_17
          split: validation
          args: wnut_17
        metrics:
          - name: Precision
            type: precision
            value: 0.656957928802589
          - name: Recall
            type: recall
            value: 0.48564593301435405
          - name: F1
            type: f1
            value: 0.5584594222833563
          - name: Accuracy
            type: accuracy
            value: 0.933951453276383

bert-finetuned-ner-Colab

This model is a fine-tuned version of Babelscape/wikineural-multilingual-ner on the wnut_17 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3577
  • Precision: 0.6570
  • Recall: 0.4856
  • F1: 0.5585
  • Accuracy: 0.9340

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 1.0 425 0.3191 0.6465 0.4091 0.5011 0.9273
0.1595 2.0 850 0.3320 0.6719 0.4629 0.5482 0.9316
0.0681 3.0 1275 0.3577 0.6570 0.4856 0.5585 0.9340

Framework versions

  • Transformers 4.32.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3