metadata

base_model: layoutlmv3
tags:
  - generated_from_trainer
datasets:
  - mp-02/cord
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-cord
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: mp-02/cord
          type: mp-02/cord
        metrics:
          - name: Precision
            type: precision
            value: 0.7572254335260116
          - name: Recall
            type: recall
            value: 0.8136645962732919
          - name: F1
            type: f1
            value: 0.784431137724551
          - name: Accuracy
            type: accuracy
            value: 0.7975382003395586

layoutlmv3-finetuned-cord

This model is a fine-tuned version of layoutlmv3 on the mp-02/cord dataset. It achieves the following results on the evaluation set:

Loss: 1.0695
Precision: 0.7572
Recall: 0.8137
F1: 0.7844
Accuracy: 0.7975

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: 1e-06
train_batch_size: 10
eval_batch_size: 10
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
2.7217	6.25	500	1.8788	0.5168	0.6095	0.5593	0.5883
1.7562	12.5	1000	1.4443	0.5337	0.6576	0.5892	0.6795
1.4387	18.75	1500	1.2162	0.6981	0.7811	0.7373	0.7746
1.2728	25.0	2000	1.1030	0.7473	0.8106	0.7777	0.7941
1.1902	31.25	2500	1.0695	0.7572	0.8137	0.7844	0.7975

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu118
Datasets 2.21.0
Tokenizers 0.19.1