Edit model card

ner-classification

This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2699
  • Precision: 0.5422
  • Recall: 0.3336
  • F1: 0.4131
  • Accuracy: 0.9439

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: 16
  • 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 1.0 213 0.2797 0.5105 0.2484 0.3342 0.9386
No log 2.0 426 0.2636 0.5493 0.3151 0.4005 0.9430
0.1938 3.0 639 0.2699 0.5422 0.3336 0.4131 0.9439

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu102
  • Datasets 2.4.0
  • Tokenizers 0.12.1
Downloads last month
8

Dataset used to train oyvindgrutle/ner-classification

Evaluation results