metadata
base_model: microsoft/layoutlm-base-uncased
tags:
- generated_from_trainer
model-index:
- name: layoutlm-funsd
results: []
layoutlm-funsd
This model is a fine-tuned version of microsoft/layoutlm-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0668
- Number-a: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4}
- Number-q: {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4}
- Overall Precision: 0.0
- Overall Recall: 0.0
- Overall F1: 0.0
- Overall Accuracy: 0.9848
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Number-a | Number-q | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|---|---|---|---|---|---|---|---|---|---|
| 1.1627 | 1.0 | 1 | 1.1422 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.2713 |
| 1.1655 | 2.0 | 2 | 1.1422 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.2713 |
| 1.1695 | 3.0 | 3 | 1.1422 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.2713 |
| 1.1661 | 4.0 | 4 | 0.8227 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.8093 |
| 0.8478 | 5.0 | 5 | 0.5718 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9744 |
| 0.5975 | 6.0 | 6 | 0.3821 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.4052 | 7.0 | 7 | 0.2537 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.2676 | 8.0 | 8 | 0.1673 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.1775 | 9.0 | 9 | 0.1173 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.1266 | 10.0 | 10 | 0.0942 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.1017 | 11.0 | 11 | 0.0842 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.0891 | 12.0 | 12 | 0.0786 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.0845 | 13.0 | 13 | 0.0741 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.0788 | 14.0 | 14 | 0.0702 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
| 0.0763 | 15.0 | 15 | 0.0668 | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | {'precision': 0.0, 'recall': 0.0, 'f1': 0.0, 'number': 4} | 0.0 | 0.0 | 0.0 | 0.9848 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0