metadata

library_name: transformers
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: 0.9672131147540983
          - name: Recall
            type: recall
            value: 0.9776304888152444
          - name: F1
            type: f1
            value: 0.9723939019365472
          - name: Accuracy
            type: accuracy
            value: 0.9766697163769442

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: 0.1292
Precision: 0.9672
Recall: 0.9776
F1: 0.9724
Accuracy: 0.9767

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: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	3.125	250	0.6018	0.8218	0.8633	0.8420	0.8577
1.0098	6.25	500	0.2695	0.9205	0.9495	0.9347	0.9451
1.0098	9.375	750	0.1813	0.9528	0.9693	0.9610	0.9639
0.1993	12.5	1000	0.1557	0.9616	0.9743	0.9679	0.9739
0.1993	15.625	1250	0.1749	0.9608	0.9743	0.9675	0.9703
0.0787	18.75	1500	0.1482	0.9616	0.9743	0.9679	0.9730
0.0787	21.875	1750	0.1288	0.9640	0.9751	0.9695	0.9762
0.0433	25.0	2000	0.1292	0.9672	0.9776	0.9724	0.9767
0.0433	28.125	2250	0.1372	0.9623	0.9735	0.9679	0.9735
0.031	31.25	2500	0.1408	0.9631	0.9743	0.9687	0.9730

Framework versions

Transformers 4.44.2
Pytorch 2.4.0+cu118
Datasets 2.21.0
Tokenizers 0.19.1