metadata

license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
  - generated_from_trainer
datasets:
  - format_dataset
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: test
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: format_dataset
          type: format_dataset
          config: assesment dataset
          split: test
          args: assesment dataset
        metrics:
          - name: Precision
            type: precision
            value: 0.8869778869778869
          - name: Recall
            type: recall
            value: 0.9025
          - name: F1
            type: f1
            value: 0.8946716232961586
          - name: Accuracy
            type: accuracy
            value: 0.9977016777752241

test

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

Loss: 0.0089
Precision: 0.8870
Recall: 0.9025
F1: 0.8947
Accuracy: 0.9977

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: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.62	100	0.0405	0.0	0.0	0.0	0.9877
No log	1.25	200	0.0170	0.7538	0.735	0.7443	0.9949
No log	1.88	300	0.0131	0.7261	0.875	0.7937	0.9956
No log	2.5	400	0.0123	0.7692	0.85	0.8076	0.9959
0.0271	3.12	500	0.0105	0.8098	0.905	0.8548	0.9968
0.0271	3.75	600	0.0106	0.8460	0.8925	0.8686	0.9972
0.0271	4.38	700	0.0086	0.8504	0.895	0.8721	0.9973
0.0271	5.0	800	0.0109	0.8871	0.845	0.8656	0.9972
0.0271	5.62	900	0.0085	0.8883	0.895	0.8917	0.9977
0.0042	6.25	1000	0.0089	0.8870	0.9025	0.8947	0.9977

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.0+cu121
Datasets 2.16.1
Tokenizers 0.15.1