jpino's picture
update model card README.md
bb490f7
metadata
tags:
  - generated_from_trainer
datasets:
  - data_registros_layoutv3
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-registros_100
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: data_registros_layoutv3
          type: data_registros_layoutv3
          config: default
          split: test
          args: default
        metrics:
          - name: Precision
            type: precision
            value: 0.9967585089141004
          - name: Recall
            type: recall
            value: 0.9951456310679612
          - name: F1
            type: f1
            value: 0.9959514170040485
          - name: Accuracy
            type: accuracy
            value: 0.999531542785759

layoutlmv3-finetuned-registros_100

This model was trained from scratch on the data_registros_layoutv3 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0050
  • Precision: 0.9968
  • Recall: 0.9951
  • F1: 0.9960
  • Accuracy: 0.9995

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: 5e-06
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 600

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 4.35 100 0.0106 0.9871 0.9935 0.9903 0.9991
No log 8.7 200 0.0073 0.9984 0.9968 0.9976 0.9997
No log 13.04 300 0.0061 0.9968 0.9968 0.9968 0.9997
No log 17.39 400 0.0048 0.9968 0.9984 0.9976 0.9997
0.0109 21.74 500 0.0053 0.9968 0.9968 0.9968 0.9997
0.0109 26.09 600 0.0050 0.9968 0.9951 0.9960 0.9995

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.12.0
  • Tokenizers 0.13.3