lilt-en-funsd-custom

This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the mydata dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0023
  • In: {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 2}
  • Ear: {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2}
  • Overall Precision: 0.6
  • Overall Recall: 0.75
  • Overall F1: 0.6667
  • Overall Accuracy: 0.9984

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: 200
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss In Ear Overall Precision Overall Recall Overall F1 Overall Accuracy
0.1628 25.0 50 0.0023 {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 2} {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} 0.6 0.75 0.6667 0.9984
0.0002 50.0 100 0.0015 {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 2} {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} 0.6 0.75 0.6667 0.9984
0.0001 75.0 150 0.0020 {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 2} {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} 0.6 0.75 0.6667 0.9984
0.0 100.0 200 0.0020 {'precision': 0.5, 'recall': 0.5, 'f1': 0.5, 'number': 2} {'precision': 0.6666666666666666, 'recall': 1.0, 'f1': 0.8, 'number': 2} 0.6 0.75 0.6667 0.9984

Framework versions

  • Transformers 4.30.0.dev0
  • Pytorch 1.8.0+cu101
  • Datasets 2.12.0
  • Tokenizers 0.13.3
Downloads last month
10
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.