|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- funsd-layoutlmv3 |
|
model-index: |
|
- name: lilt-en-funsd |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# lilt-en-funsd |
|
|
|
This model is a fine-tuned version of [SCUT-DLVCLab/lilt-roberta-en-base](https://huggingface.co/SCUT-DLVCLab/lilt-roberta-en-base) on the funsd-layoutlmv3 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9065 |
|
- Answer: {'precision': 0.834096109839817, 'recall': 0.8922888616891065, 'f1': 0.8622117090479007, 'number': 817} |
|
- Header: {'precision': 0.5319148936170213, 'recall': 0.42016806722689076, 'f1': 0.4694835680751173, 'number': 119} |
|
- Question: {'precision': 0.8570175438596491, 'recall': 0.9071494893221913, 'f1': 0.8813712223725756, 'number': 1077} |
|
- Overall Precision: 0.8330 |
|
- Overall Recall: 0.8723 |
|
- Overall F1: 0.8522 |
|
- Overall Accuracy: 0.7918 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:| |
|
| 0.7017 | 5.26 | 100 | 0.7391 | {'precision': 0.8216340621403913, 'recall': 0.8739290085679314, 'f1': 0.8469750889679716, 'number': 817} | {'precision': 0.4533333333333333, 'recall': 0.2857142857142857, 'f1': 0.3505154639175258, 'number': 119} | {'precision': 0.8234323432343235, 'recall': 0.9266480965645311, 'f1': 0.8719965050240279, 'number': 1077} | 0.8098 | 0.8674 | 0.8376 | 0.8073 | |
|
| 0.1656 | 10.53 | 200 | 0.9065 | {'precision': 0.834096109839817, 'recall': 0.8922888616891065, 'f1': 0.8622117090479007, 'number': 817} | {'precision': 0.5319148936170213, 'recall': 0.42016806722689076, 'f1': 0.4694835680751173, 'number': 119} | {'precision': 0.8570175438596491, 'recall': 0.9071494893221913, 'f1': 0.8813712223725756, 'number': 1077} | 0.8330 | 0.8723 | 0.8522 | 0.7918 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
