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
        metrics:
          - name: Precision
            type: precision
            value: 0.9227969559942649
          - name: Recall
            type: recall
            value: 0.9360107394563151
          - name: F1
            type: f1
            value: 0.9293568810396535
          - name: Accuracy
            type: accuracy
            value: 0.9833034139831922
      - task:
          type: token-classification
          name: Token Classification
        dataset:
          name: conll2003
          type: conll2003
          config: conll2003
          split: test
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.973914094330502
            verified: true
          - name: Precision
            type: precision
            value: 0.9791360147483736
            verified: true
          - name: Recall
            type: recall
            value: 0.9793269742207723
            verified: true
          - name: F1
            type: f1
            value: 0.9792314851748437
            verified: true
          - name: loss
            type: loss
            value: 0.10710480064153671
            verified: true

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: 0.0614
Precision: 0.9228
Recall: 0.9360
F1: 0.9294
Accuracy: 0.9833

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
0.2433	1.0	878	0.0732	0.9079	0.9190	0.9134	0.9795
0.0553	2.0	1756	0.0599	0.9170	0.9333	0.9251	0.9826
0.0305	3.0	2634	0.0614	0.9228	0.9360	0.9294	0.9833

Framework versions

Transformers 4.18.0
Pytorch 1.10.0+cu111
Datasets 2.0.0
Tokenizers 0.11.6