bert-base-uncased-ner

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

  • Loss: 2.1258
  • Precision: 0.0269
  • Recall: 0.1379
  • F1: 0.0451
  • Accuracy: 0.1988

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: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 4 2.1296 0.0270 0.1389 0.0452 0.1942
No log 2.0 8 2.1258 0.0269 0.1379 0.0451 0.1988

Framework versions

  • Transformers 4.8.2
  • Pytorch 1.8.1+cu111
  • Datasets 1.8.0
  • Tokenizers 0.10.3
Downloads last month
17
Hosted inference API
Token Classification
This model can be loaded on the Inference API on-demand.