layoutlmv3-finetuned-trf1

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: 0.0524
• Precision: 0.9891
• Recall: 0.9785
• F1: 0.9838
• Accuracy: 0.9892

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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.8787	12.5	100	0.6080	0.9667	0.9355	0.9508	0.9677
0.2482	25.0	200	0.1501	0.9891	0.9785	0.9838	0.9892
0.0882	37.5	300	0.0934	0.9780	0.9570	0.9674	0.9785
0.0482	50.0	400	0.0759	0.9780	0.9570	0.9674	0.9785
0.0351	62.5	500	0.0620	0.9780	0.9570	0.9674	0.9785
0.0285	75.0	600	0.0545	0.9891	0.9785	0.9838	0.9892
0.0243	87.5	700	0.0578	0.9780	0.9570	0.9674	0.9785
0.0234	100.0	800	0.0632	0.9780	0.9570	0.9674	0.9785
0.0212	112.5	900	0.0682	0.9780	0.9570	0.9674	0.9785
0.0201	125.0	1000	0.0524	0.9891	0.9785	0.9838	0.9892

Framework versions

• Transformers 4.57.3
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1