metadata

license: cc-by-nc-sa-4.0
tags:
  - generated_from_trainer
datasets:
  - cord-layoutlmv3
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv3-finetuned-cord_800
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: cord-layoutlmv3
          type: cord-layoutlmv3
          config: cord
          split: train
          args: cord
        metrics:
          - name: Precision
            type: precision
            value: 0.9445266272189349
          - name: Recall
            type: recall
            value: 0.9558383233532934
          - name: F1
            type: f1
            value: 0.9501488095238095
          - name: Accuracy
            type: accuracy
            value: 0.9605263157894737

layoutlmv3-finetuned-cord_800

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

Loss: 0.2042
Precision: 0.9445
Recall: 0.9558
F1: 0.9501
Accuracy: 0.9605

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: 5
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.56	250	0.9737	0.7787	0.8166	0.7972	0.8188
1.3706	3.12	500	0.5489	0.8480	0.8645	0.8562	0.8680
1.3706	4.69	750	0.3857	0.8913	0.9087	0.8999	0.9147
0.3693	6.25	1000	0.3192	0.9117	0.9274	0.9195	0.9317
0.3693	7.81	1250	0.2816	0.9189	0.9326	0.9257	0.9355
0.1903	9.38	1500	0.2521	0.9277	0.9409	0.9342	0.9465
0.1903	10.94	1750	0.2353	0.9357	0.9476	0.9416	0.9550
0.1231	12.5	2000	0.2361	0.9293	0.9446	0.9369	0.9516
0.1231	14.06	2250	0.2194	0.9402	0.9528	0.9465	0.9576
0.0766	15.62	2500	0.2133	0.9416	0.9528	0.9472	0.9580
0.0766	17.19	2750	0.2117	0.9438	0.9558	0.9498	0.9597
0.0585	18.75	3000	0.2152	0.9417	0.9551	0.9483	0.9605
0.0585	20.31	3250	0.2070	0.9431	0.9551	0.9491	0.9588
0.0454	21.88	3500	0.2093	0.9489	0.9588	0.9538	0.9622
0.0454	23.44	3750	0.2034	0.9453	0.9566	0.9509	0.9610
0.0409	25.0	4000	0.2042	0.9445	0.9558	0.9501	0.9605

Framework versions

Transformers 4.21.2
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1