layoutlmv3-finetuned-invoice_ConControl_v2

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: 0.0090
• Precision: 0.9805
• Recall: 0.9853
• F1: 0.9829
• Accuracy: 0.9989

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: 8
• eval_batch_size: 8
• 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: 200
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	15	0.1034	0.8095	0.1667	0.2764	0.9744
No log	2.0	30	0.0416	0.605	0.5931	0.5990	0.9862
No log	3.0	45	0.0196	0.8373	0.8578	0.8475	0.9946
No log	4.0	60	0.0161	0.9120	0.9657	0.9381	0.9970
No log	5.0	75	0.0090	0.9805	0.9853	0.9829	0.9989
No log	6.0	90	0.0109	0.9706	0.9706	0.9706	0.9982
No log	7.0	105	0.0108	0.9663	0.9853	0.9757	0.9985
No log	8.0	120	0.0099	0.9757	0.9853	0.9805	0.9988
No log	9.0	135	0.0108	0.9663	0.9853	0.9757	0.9985
No log	10.0	150	0.0108	0.9663	0.9853	0.9757	0.9985
No log	11.0	165	0.0118	0.9663	0.9853	0.9757	0.9985
No log	12.0	180	0.0126	0.9663	0.9853	0.9757	0.9985
No log	13.0	195	0.0124	0.9662	0.9804	0.9732	0.9983
No log	13.3333	200	0.0124	0.9662	0.9804	0.9732	0.9983

Framework versions

• Transformers 4.50.0
• Pytorch 2.5.1+cu121
• Datasets 3.4.1
• Tokenizers 0.21.1