layoutlmv3-finetuned-invoice_ConControl

This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0254
• Precision: 0.9191
• Recall: 0.8503
• F1: 0.8833
• Accuracy: 0.9944

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	8	0.1907	0.0	0.0	0.0	0.9699
No log	2.0	16	0.1523	0.0	0.0	0.0	0.9699
No log	3.0	24	0.1077	1.0	0.3422	0.5100	0.9802
No log	4.0	32	0.0731	0.8488	0.3904	0.5348	0.9817
No log	5.0	40	0.0552	0.7929	0.5936	0.6789	0.9876
No log	6.0	48	0.0431	0.9610	0.7914	0.8680	0.9934
No log	7.0	56	0.0349	0.9434	0.8021	0.8671	0.9932
No log	8.0	64	0.0304	0.9554	0.8021	0.8721	0.9936
No log	9.0	72	0.0279	0.9231	0.8342	0.8764	0.9944
No log	10.0	80	0.0268	0.9176	0.8342	0.8739	0.9942
No log	11.0	88	0.0264	0.9029	0.8449	0.8729	0.9941
No log	12.0	96	0.0255	0.9075	0.8396	0.8722	0.9941
No log	12.5	100	0.0254	0.9191	0.8503	0.8833	0.9944

Framework versions

• Transformers 4.50.0
• Pytorch 2.6.0+cu118
• Datasets 3.4.1
• Tokenizers 0.21.1