layoutlmv3-finetuned-binary-cordv2

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

• Loss: 0.0062
• Precision: 0.9890
• Recall: 0.9963
• F1: 0.9926
• Accuracy: 0.9986

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: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.5625	250	0.0103	0.9779	0.9852	0.9815	0.9963
0.0581	3.125	500	0.0132	0.9781	0.9926	0.9853	0.9973
0.0581	4.6875	750	0.0066	0.9781	0.9926	0.9853	0.9977
0.0097	6.25	1000	0.0185	0.9704	0.9704	0.9704	0.9954
0.0097	7.8125	1250	0.0130	0.9745	0.9889	0.9816	0.9968
0.0048	9.375	1500	0.0072	0.9890	0.9963	0.9926	0.9986
0.0048	10.9375	1750	0.0044	0.9781	0.9926	0.9853	0.9982
0.0029	12.5	2000	0.0092	0.9779	0.9852	0.9815	0.9973
0.0029	14.0625	2250	0.0080	0.9853	0.9926	0.9889	0.9982
0.0013	15.625	2500	0.0062	0.9890	0.9963	0.9926	0.9986

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1