metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - wikiann
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: wiki_hu_ner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: wikiann
          type: wikiann
          config: hu
          split: validation
          args: hu
        metrics:
          - name: Precision
            type: precision
            value: 0.8669236159775753
          - name: Recall
            type: recall
            value: 0.8782479057219935
          - name: F1
            type: f1
            value: 0.872549019607843
          - name: Accuracy
            type: accuracy
            value: 0.9632061446977205

wiki_hu_ner

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

Loss: 0.1585
Precision: 0.8669
Recall: 0.8782
F1: 0.8725
Accuracy: 0.9632

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.2429	1.0	1250	0.1849	0.8047	0.8153	0.8100	0.9448
0.1371	2.0	2500	0.1505	0.8455	0.8577	0.8516	0.9576
0.0986	3.0	3750	0.1516	0.8520	0.8708	0.8613	0.9603
0.0695	4.0	5000	0.1500	0.8656	0.8745	0.8700	0.9624
0.0489	5.0	6250	0.1585	0.8669	0.8782	0.8725	0.9632

Framework versions

Transformers 4.32.0
Pytorch 2.0.1+cu118
Datasets 2.14.4
Tokenizers 0.13.3