layoutlmv3-large-cord

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: 0.1616
  • Precision: 0.9526
  • Recall: 0.9482
  • F1: 0.9504
  • Accuracy: 0.9677

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: 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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 0.25 100 0.5321 0.7584 0.7859 0.7719 0.8224
No log 0.5 200 0.4949 0.8091 0.8354 0.8221 0.8683
No log 0.75 300 0.3478 0.8668 0.8648 0.8658 0.8916
No log 1.0 400 0.5194 0.75 0.7117 0.7304 0.8513
0.6065 1.25 500 0.3052 0.9059 0.9003 0.9031 0.9341
0.6065 1.5 600 0.2427 0.9245 0.9173 0.9209 0.9443
0.6065 1.75 700 0.2372 0.9174 0.9181 0.9177 0.9477
0.6065 2.0 800 0.2044 0.9247 0.9212 0.9230 0.9494
0.6065 2.25 900 0.1847 0.9442 0.9413 0.9427 0.9613
0.1862 2.5 1000 0.1616 0.9526 0.9482 0.9504 0.9677

Framework versions

  • Transformers 4.36.0
  • Pytorch 2.0.0
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
34
Safetensors
Model size
357M params
Tensor type
F32
·
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.

Model tree for cuongdz01/layoutlmv3-large-cord

Finetuned
(6)
this model