Edit model card

model-v2-2024-05-24

This model is a fine-tuned version of microsoft/layoutlmv3-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6290
  • Precision: 0.7352
  • Recall: 0.7187
  • F1: 0.7268
  • Accuracy: 0.8676

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: 2
  • eval_batch_size: 2
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • training_steps: 1000

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.03 100 1.3265 0.3804 0.1879 0.2516 0.7083
No log 2.06 200 0.8735 0.6222 0.5177 0.5652 0.8107
No log 3.09 300 0.7081 0.6899 0.6206 0.6534 0.8445
No log 4.12 400 0.6085 0.7168 0.6643 0.6896 0.8574
0.9891 5.15 500 0.6386 0.7164 0.6868 0.7013 0.8532
0.9891 6.19 600 0.6020 0.6815 0.7057 0.6934 0.8483
0.9891 7.22 700 0.6030 0.7215 0.7045 0.7129 0.8623
0.9891 8.25 800 0.6220 0.7179 0.7128 0.7153 0.8623
0.9891 9.28 900 0.6269 0.7313 0.7270 0.7291 0.8672
0.3198 10.31 1000 0.6290 0.7352 0.7187 0.7268 0.8676

Framework versions

  • Transformers 4.29.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.13.3
Downloads last month
3
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.