Edit model card

NLP-TokenClass-NER

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

  • Loss: 0.3741
  • Precision: 0.8120
  • Recall: 0.8425
  • F1: 0.8269
  • Accuracy: 0.9255

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: 1

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.0902 1.0 2500 0.3741 0.8120 0.8425 0.8269 0.9255

Framework versions

  • Transformers 4.26.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.10.1
  • Tokenizers 0.13.2
Downloads last month
1

Dataset used to train Endika99/NLP-TokenClass-NER

Evaluation results