metadata
license: mit
tags:
- generated_from_trainer
datasets:
- funsd-layoutlmv3
model-index:
- name: lilt-en-funsd
results: []
lilt-en-funsd
This model is a fine-tuned version of SCUT-DLVCLab/lilt-roberta-en-base on the funsd-layoutlmv3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8811
- Answer: {'precision': 0.8316268486916951, 'recall': 0.8947368421052632, 'f1': 0.8620283018867924, 'number': 817}
- Header: {'precision': 0.4777777777777778, 'recall': 0.36134453781512604, 'f1': 0.41148325358851673, 'number': 119}
- Question: {'precision': 0.8480349344978166, 'recall': 0.9015784586815228, 'f1': 0.873987398739874, 'number': 1077}
- Overall Precision: 0.8254
- Overall Recall: 0.8669
- Overall F1: 0.8457
- Overall Accuracy: 0.7806
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
- training_steps: 200
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Answer | Header | Question | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|---|
| 0.7083 | 5.26 | 100 | 0.7032 | {'precision': 0.8124293785310734, 'recall': 0.8800489596083231, 'f1': 0.8448883666274971, 'number': 817} | {'precision': 0.4852941176470588, 'recall': 0.2773109243697479, 'f1': 0.35294117647058826, 'number': 119} | {'precision': 0.8360375747224594, 'recall': 0.9090064995357474, 'f1': 0.8709964412811388, 'number': 1077} | 0.8150 | 0.8599 | 0.8368 | 0.8089 |
| 0.1639 | 10.53 | 200 | 0.8811 | {'precision': 0.8316268486916951, 'recall': 0.8947368421052632, 'f1': 0.8620283018867924, 'number': 817} | {'precision': 0.4777777777777778, 'recall': 0.36134453781512604, 'f1': 0.41148325358851673, 'number': 119} | {'precision': 0.8480349344978166, 'recall': 0.9015784586815228, 'f1': 0.873987398739874, 'number': 1077} | 0.8254 | 0.8669 | 0.8457 | 0.7806 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2