README.md

metadata

library_name: transformers
base_model: layoutlmv3
tags:
  - generated_from_trainer
datasets:
  - mp-02/cord-sroie
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-base-cord-sroie
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: mp-02/cord-sroie
          type: mp-02/cord-sroie
        metrics:
          - name: Precision
            type: precision
            value: 0.9105022831050228
          - name: Recall
            type: recall
            value: 0.9447998104714522
          - name: F1
            type: f1
            value: 0.9273340309266364
          - name: Accuracy
            type: accuracy
            value: 0.9738126147097005

layoutlmv3-base-cord-sroie

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

• Loss: 0.0936
• Precision: 0.9105
• Recall: 0.9448
• F1: 0.9273
• Accuracy: 0.9738

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.7937	100	0.4396	0.6271	0.6015	0.6140	0.9064
No log	1.5873	200	0.2500	0.8669	0.8394	0.8529	0.9508
No log	2.3810	300	0.1517	0.8682	0.9050	0.8862	0.9634
No log	3.1746	400	0.1346	0.8694	0.9339	0.9005	0.9645
0.6691	3.9683	500	0.0943	0.9369	0.9325	0.9347	0.9778
0.6691	4.7619	600	0.0922	0.9049	0.9491	0.9265	0.9742
0.6691	5.5556	700	0.1106	0.8913	0.9540	0.9216	0.9717
0.6691	6.3492	800	0.0875	0.9091	0.9552	0.9316	0.9755
0.6691	7.1429	900	0.0958	0.8977	0.9623	0.9289	0.9743
0.1055	7.9365	1000	0.0936	0.9105	0.9448	0.9273	0.9738
0.1055	8.7302	1100	0.1035	0.9289	0.9415	0.9352	0.9766
0.1055	9.5238	1200	0.1115	0.9081	0.9507	0.9289	0.9739

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3