layoutlmv3-ap7_12_stitched_8_batch_4e5

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: 0.0135
• Precision: 0.6389
• Recall: 0.92
• F1: 0.7541
• Accuracy: 0.9970

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: 4e-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
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.3032	25.0	250	0.0178	0.6818	0.6	0.6383	0.9965
0.0076	50.0	500	0.0185	0.5938	0.76	0.6667	0.9960
0.0021	75.0	750	0.0130	0.6216	0.92	0.7419	0.9967
0.0012	100.0	1000	0.0135	0.6389	0.92	0.7541	0.9970

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.1
• Tokenizers 0.21.1