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: 0.9461305007587253
          - name: Recall
            type: recall
            value: 0.968167701863354
          - name: F1
            type: f1
            value: 0.9570222563315426
          - name: Accuracy
            type: accuracy
            value: 0.9592529711375212

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: 0.2268
Precision: 0.9461
Recall: 0.9682
F1: 0.9570
Accuracy: 0.9593

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: 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
1.5249	6.25	500	0.6825	0.8146	0.8595	0.8364	0.8434
0.5103	12.5	1000	0.3562	0.9058	0.9410	0.9231	0.9312
0.2872	18.75	1500	0.2750	0.9337	0.9620	0.9476	0.9508
0.2008	25.0	2000	0.2383	0.9483	0.9689	0.9585	0.9576
0.1611	31.25	2500	0.2268	0.9461	0.9682	0.9570	0.9593

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu118
Datasets 2.21.0
Tokenizers 0.19.1