Edit model card

layoutlmv3-cord-ner

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

  • Loss: 0.1215
  • Precision: 0.9448
  • Recall: 0.9520
  • F1: 0.9484
  • Accuracy: 0.9762

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: 5e-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: 10

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 113 0.1771 0.8485 0.8925 0.8700 0.9393
No log 2.0 226 0.1584 0.8915 0.9146 0.9029 0.9524
No log 3.0 339 0.1153 0.9160 0.9309 0.9234 0.9686
No log 4.0 452 0.1477 0.9110 0.9136 0.9123 0.9592
0.1562 5.0 565 0.0861 0.9363 0.9443 0.9403 0.9741
0.1562 6.0 678 0.1165 0.9109 0.9415 0.9259 0.9673
0.1562 7.0 791 0.1280 0.9278 0.9367 0.9322 0.9707
0.1562 8.0 904 0.1122 0.9462 0.9453 0.9458 0.9762
0.0224 9.0 1017 0.1265 0.9431 0.9539 0.9485 0.9771
0.0224 10.0 1130 0.1215 0.9448 0.9520 0.9484 0.9762

Framework versions

  • Transformers 4.20.0.dev0
  • Pytorch 1.11.0
  • Datasets 2.1.0
  • Tokenizers 0.12.1
Downloads last month
5
Hosted inference API
Token Classification
Examples
Examples
This model can be loaded on the Inference API on-demand.