README.md

metadata

license: cc-by-nc-sa-4.0
tags:
  - generated_from_trainer
datasets:
  - generated
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-invoice
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: generated
          type: generated
          config: sroie
          split: test
          args: sroie
        metrics:
          - name: Precision
            type: precision
            value: 0.9959514170040485
          - name: Recall
            type: recall
            value: 0.9979716024340771
          - name: F1
            type: f1
            value: 0.9969604863221885
          - name: Accuracy
            type: accuracy
            value: 0.9995786812723826

layoutlmv3-finetuned-invoice

This model is a fine-tuned version of microsoft/layoutlmv3-base on the generated dataset. It achieves the following results on the evaluation set:

• Loss: 0.0070
• Precision: 0.9960
• Recall: 0.9980
• F1: 0.9970
• Accuracy: 0.9996

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: 2
• eval_batch_size: 2
• 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	2.0	100	0.0947	0.892	0.9047	0.8983	0.9886
No log	4.0	200	0.0232	0.972	0.9858	0.9789	0.9971
No log	6.0	300	0.0175	0.972	0.9858	0.9789	0.9971
No log	8.0	400	0.0130	0.972	0.9858	0.9789	0.9971
0.1292	10.0	500	0.0070	0.9960	0.9980	0.9970	0.9996
0.1292	12.0	600	0.0081	0.9837	0.9817	0.9827	0.9975
0.1292	14.0	700	0.0045	0.9980	0.9959	0.9970	0.9996
0.1292	16.0	800	0.0026	0.9980	0.9980	0.9980	0.9998
0.1292	18.0	900	0.0024	0.9980	0.9980	0.9980	0.9998
0.0066	20.0	1000	0.0030	0.9960	0.9980	0.9970	0.9996
0.0066	22.0	1100	0.0025	0.9980	0.9980	0.9980	0.9998
0.0066	24.0	1200	0.0019	0.9980	0.9980	0.9980	0.9998
0.0066	26.0	1300	0.0019	0.9980	0.9980	0.9980	0.9998
0.0066	28.0	1400	0.0028	0.9960	0.9980	0.9970	0.9996
0.0026	30.0	1500	0.0022	0.9960	0.9980	0.9970	0.9996
0.0026	32.0	1600	0.0023	0.9960	0.9980	0.9970	0.9996
0.0026	34.0	1700	0.0021	0.9960	0.9980	0.9970	0.9996
0.0026	36.0	1800	0.0033	0.9960	0.9980	0.9970	0.9996
0.0026	38.0	1900	0.0032	0.9960	0.9980	0.9970	0.9996
0.0019	40.0	2000	0.0032	0.9960	0.9980	0.9970	0.9996

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2