layoutlmv2-er-ner / README.md
renjithks's picture
update model card README.md
ac373ba
|
raw
history blame
2.35 kB
metadata
license: cc-by-nc-sa-4.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: layoutlmv2-er-ner
    results: []

layoutlmv2-er-ner

This model is a fine-tuned version of renjithks/layoutlmv2-cord-ner on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1710
  • Precision: 0.6987
  • Recall: 0.6968
  • F1: 0.6977
  • Accuracy: 0.9622

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 22 0.2635 0.4513 0.3724 0.4080 0.9282
No log 2.0 44 0.2537 0.4459 0.4824 0.4634 0.9327
No log 3.0 66 0.2027 0.6367 0.5487 0.5894 0.9486
No log 4.0 88 0.1943 0.6126 0.6446 0.6282 0.9547
No log 5.0 110 0.1840 0.6644 0.6756 0.6699 0.9559
No log 6.0 132 0.1719 0.6819 0.6319 0.6559 0.9610
No log 7.0 154 0.1698 0.6471 0.6827 0.6644 0.9598
No log 8.0 176 0.1767 0.7022 0.6685 0.6850 0.9604
No log 9.0 198 0.1661 0.6973 0.6953 0.6963 0.9630
No log 10.0 220 0.1710 0.6987 0.6968 0.6977 0.9622

Framework versions

  • Transformers 4.16.2
  • Pytorch 1.9.0+cu111
  • Datasets 1.18.4
  • Tokenizers 0.11.6