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: 0.9572519083969465
          - name: Recall
            type: recall
            value: 0.9736024844720497
          - name: F1
            type: f1
            value: 0.9653579676674365
          - name: Accuracy
            type: accuracy
            value: 0.9673174872665535

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: 0.1831
Precision: 0.9573
Recall: 0.9736
F1: 0.9654
Accuracy: 0.9673

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-05
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: 2000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	3.125	250	0.7551	0.7974	0.8587	0.8269	0.8544
1.1001	6.25	500	0.3822	0.8846	0.9286	0.9061	0.9215
1.1001	9.375	750	0.2750	0.9334	0.9581	0.9456	0.9444
0.2309	12.5	1000	0.2072	0.9439	0.9674	0.9555	0.9605
0.2309	15.625	1250	0.1934	0.9500	0.9728	0.9613	0.9652
0.1003	18.75	1500	0.1898	0.9602	0.9736	0.9668	0.9665
0.1003	21.875	1750	0.2032	0.9542	0.9705	0.9623	0.9631
0.0637	25.0	2000	0.1831	0.9573	0.9736	0.9654	0.9673

Framework versions

Transformers 4.42.4
Pytorch 2.4.0+cu118
Datasets 2.21.0
Tokenizers 0.19.1