This model is a fine-tuned version of microsoft/layoutlmv3-base on the cord-layoutlmv3 dataset.
It achieves the following results on the evaluation set:
eval_loss: 1.0986
eval_precision: 0.6521
eval_recall: 0.7365
eval_f1: 0.6917
eval_accuracy: 0.7593
eval_runtime: 182.1992
eval_samples_per_second: 0.549
eval_steps_per_second: 0.11
epoch: 1.56
step: 250
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: 5
eval_batch_size: 5
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
