metadata

license: mit
base_model: microsoft/layoutlm-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: layoutlmv3-custom_no_text
    results: []

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: 0.3487
eval_noise: {'precision': 0.6914893617021277, 'recall': 0.7210776545166403, 'f1': 0.7059736229635376, 'number': 631}
eval_signal: {'precision': 0.684931506849315, 'recall': 0.7142857142857143, 'f1': 0.6993006993006993, 'number': 630}
eval_overall_precision: 0.6882
eval_overall_recall: 0.7177
eval_overall_f1: 0.7026
eval_overall_accuracy: 0.9325
eval_runtime: 0.9604
eval_samples_per_second: 37.484
eval_steps_per_second: 5.206
epoch: 24.0
step: 432

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