metadata

tags:
  - generated_from_trainer
datasets:
  - mp-02/funsd
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-funsd
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: mp-02/funsd
          type: mp-02/funsd
        metrics:
          - name: Precision
            type: precision
            value: 0.9059871350816427
          - name: Recall
            type: recall
            value: 0.9155
          - name: F1
            type: f1
            value: 0.9107187266849044
          - name: Accuracy
            type: accuracy
            value: 0.8407211759301791

layoutlmv3-finetuned-funsd

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

Loss: 0.8860
Precision: 0.9060
Recall: 0.9155
F1: 0.9107
Accuracy: 0.8407

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: 4
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	2.63	100	0.6111	0.7963	0.864	0.8288	0.7987
No log	5.26	200	0.5861	0.8507	0.883	0.8665	0.8266
No log	7.89	300	0.5856	0.8654	0.9005	0.8826	0.8426
No log	10.53	400	0.6502	0.8801	0.8995	0.8897	0.8427
0.4088	13.16	500	0.7679	0.8880	0.904	0.8959	0.8373
0.4088	15.79	600	0.8371	0.8820	0.904	0.8928	0.8333
0.4088	18.42	700	0.8320	0.8931	0.9145	0.9037	0.8336
0.4088	21.05	800	0.8494	0.8969	0.9135	0.9051	0.8341
0.4088	23.68	900	0.8700	0.9005	0.914	0.9072	0.8385
0.061	26.32	1000	0.8860	0.9060	0.9155	0.9107	0.8407

Framework versions

Transformers 4.12.5
Pytorch 1.10.0+cu111
Datasets 2.13.2
Tokenizers 0.10.1