metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - article250v2_wikigold_split
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: Article_250v2_NER_Model_3Epochs_UNAUGMENTED
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: article250v2_wikigold_split
          type: article250v2_wikigold_split
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.4664981036662453
          - name: Recall
            type: recall
            value: 0.5280480824270177
          - name: F1
            type: f1
            value: 0.49536850583971004
          - name: Accuracy
            type: accuracy
            value: 0.9042507513954486

Article_250v2_NER_Model_3Epochs_UNAUGMENTED

This model is a fine-tuned version of bert-base-cased on the article250v2_wikigold_split dataset. It achieves the following results on the evaluation set:

Loss: 0.2900
Precision: 0.4665
Recall: 0.5280
F1: 0.4954
Accuracy: 0.9043

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: 8
eval_batch_size: 8
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	29	0.4904	0.1788	0.0487	0.0765	0.8034
No log	2.0	58	0.3224	0.4091	0.4825	0.4428	0.8951
No log	3.0	87	0.2900	0.4665	0.5280	0.4954	0.9043

Framework versions

Transformers 4.17.0
Pytorch 1.11.0+cu113
Datasets 2.4.0
Tokenizers 0.11.6