Edit model card

bert-to-distilbert-NER

This model is a fine-tuned version of dslim/bert-base-NER on the conll2003 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 5.9063
  • eval_precision: 0.0120
  • eval_recall: 0.0069
  • eval_f1: 0.0088
  • eval_accuracy: 0.7600
  • eval_runtime: 8.6309
  • eval_samples_per_second: 376.671
  • eval_steps_per_second: 3.012
  • epoch: 1.0
  • step: 110

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: 0.00023888106906613202
  • train_batch_size: 128
  • eval_batch_size: 128
  • seed: 33
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.19.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.2.1
  • Tokenizers 0.12.1
Downloads last month
6

Dataset used to train kushaljoseph/bert-to-distilbert-NER