layoutlmv3-custom_no_text

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

• eval_loss: 0.2406
• eval_noise: {'precision': 0.772093023255814, 'recall': 0.8019323671497585, 'f1': 0.7867298578199052, 'number': 621}
• eval_signal: {'precision': 0.7472868217054264, 'recall': 0.77491961414791, 'f1': 0.7608524072612471, 'number': 622}
• eval_overall_precision: 0.7597
• eval_overall_recall: 0.7884
• eval_overall_f1: 0.7738
• eval_overall_accuracy: 0.9518
• eval_runtime: 1.0449
• eval_samples_per_second: 34.452
• eval_steps_per_second: 4.785
• epoch: 19.0
• step: 342

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: 3e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0