layoutlmv3-ap5_3

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: 0.7181
• Precision: 0.875
• Recall: 0.7778
• F1: 0.8235
• Accuracy: 0.8889

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: 4
• eval_batch_size: 4
• 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
0.4938	62.5	250	0.7181	0.875	0.7778	0.8235	0.8889
0.0015	125.0	500	0.8105	0.875	0.7778	0.8235	0.8889
0.0009	187.5	750	0.8680	0.875	0.7778	0.8235	0.8889
0.0007	250.0	1000	0.8754	0.875	0.7778	0.8235	0.8889

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0