layoutlm-synth3 / README.md
brandaobrandisborges's picture
End of training
b2acccb
metadata
tags:
  - generated_from_trainer
model-index:
  - name: layoutlm-synth3
    results: []

layoutlm-synth3

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:

  • Loss: 0.0021
  • Ank Address: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39}
  • Ank Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39}
  • Ayee Address: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39}
  • Ayee Name: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39}
  • Icr: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39}
  • Mount: {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39}
  • Overall Precision: 1.0
  • Overall Recall: 1.0
  • Overall F1: 1.0
  • Overall Accuracy: 1.0

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: 6
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Ank Address Ank Name Ayee Address Ayee Name Icr Mount Overall Precision Overall Recall Overall F1 Overall Accuracy
0.9365 1.0 20 0.1057 {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 0.9487179487179487, 'recall': 0.9487179487179487, 'f1': 0.9487179487179487, 'number': 39} {'precision': 0.9487179487179487, 'recall': 0.9487179487179487, 'f1': 0.9487179487179487, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} 0.9829 0.9829 0.9829 0.9976
0.0449 2.0 40 0.0058 {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} 1.0 1.0 1.0 1.0
0.0075 3.0 60 0.0028 {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} 1.0 1.0 1.0 1.0
0.005 4.0 80 0.0022 {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} 1.0 1.0 1.0 1.0
0.0042 5.0 100 0.0021 {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} {'precision': 1.0, 'recall': 1.0, 'f1': 1.0, 'number': 39} 1.0 1.0 1.0 1.0

Framework versions

  • Transformers 4.27.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.10.1
  • Tokenizers 0.13.2