README.md

metadata

license: cc-by-nc-sa-4.0
tags:
  - generated_from_trainer
datasets:
  - cord-layoutlmv3
model-index:
  - name: DocumentNick
    results: []

DocumentNick

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: 0.5167
• eval_precision: 0.8758
• eval_recall: 0.8922
• eval_f1: 0.8839
• eval_accuracy: 0.8901
• eval_runtime: 10.2752
• eval_samples_per_second: 9.732
• eval_steps_per_second: 1.946
• epoch: 11.95
• step: 526

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
• lr_scheduler_type: linear
• training_steps: 2500

Framework versions

• Transformers 4.24.0
• Pytorch 1.13.0+cu116
• Datasets 2.8.0
• Tokenizers 0.13.2