zald's picture
add model
a78c2e0
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - conll2003
metrics:
  - precision
  - recall
  - f1
  - accuracy
model_index:
  - name: distilbert-base-uncased-finetuned-ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: conll2003
          type: conll2003
          args: conll2003
        metric:
          name: Accuracy
          type: accuracy
          value: 0.9835893688340985

distilbert-base-uncased-finetuned-ner

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

  • Loss: 0.0607
  • Precision: 0.9253
  • Recall: 0.9350
  • F1: 0.9301
  • Accuracy: 0.9836

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
0.237 1.0 878 0.0701 0.9131 0.9228 0.9179 0.9809
0.0509 2.0 1756 0.0617 0.9182 0.9333 0.9257 0.9826
0.0299 3.0 2634 0.0607 0.9253 0.9350 0.9301 0.9836

Framework versions

  • Transformers 4.8.2
  • Pytorch 1.8.1+cu111
  • Datasets 1.11.0
  • Tokenizers 0.10.3