layoutlmv3-finetuned-arabic_docs_v2

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: 0.0001
• Precision: 1.0
• Recall: 1.0
• F1: 1.0
• Accuracy: 1.0

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: 10
• eval_batch_size: 10
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 2500

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	6.7568	250	0.0007	1.0	1.0	1.0	1.0
0.0576	13.5135	500	0.0004	1.0	1.0	1.0	1.0
0.0576	20.2703	750	0.0002	1.0	1.0	1.0	1.0
0.0076	27.0270	1000	0.0001	1.0	1.0	1.0	1.0
0.0076	33.7838	1250	0.0001	1.0	1.0	1.0	1.0
0.0051	40.5405	1500	0.0001	1.0	1.0	1.0	1.0
0.0051	47.2973	1750	0.0001	1.0	1.0	1.0	1.0
0.0044	54.0541	2000	0.0001	1.0	1.0	1.0	1.0
0.0044	60.8108	2250	0.0001	1.0	1.0	1.0	1.0
0.0034	67.5676	2500	0.0001	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0