layoutlmv3-finetuned-arabic_books

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: 0.3112
• Precision: 0.9620
• Recall: 0.9048
• F1: 0.9325
• Accuracy: 0.9733

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	1.8519	250	0.2318	0.9620	0.9048	0.9325	0.9733
0.0888	3.7037	500	0.2139	0.9620	0.9048	0.9325	0.9733
0.0888	5.5556	750	0.2559	0.9620	0.9048	0.9325	0.9733
0.0433	7.4074	1000	0.2578	0.9494	0.8929	0.9202	0.9679
0.0433	9.2593	1250	0.2790	0.9620	0.9048	0.9325	0.9733
0.0196	11.1111	1500	0.2876	0.9620	0.9048	0.9325	0.9733
0.0196	12.9630	1750	0.2946	0.9620	0.9048	0.9325	0.9733
0.0068	14.8148	2000	0.3049	0.9620	0.9048	0.9325	0.9733
0.0068	16.6667	2250	0.3101	0.9620	0.9048	0.9325	0.9733
0.0015	18.5185	2500	0.3112	0.9620	0.9048	0.9325	0.9733

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.2
• Tokenizers 0.19.1