layoutlmv3_document_classification
This model is a fine-tuned version of microsoft/layoutlmv3-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6107
- Accuracy: 0.8859
- F1: 0.8805
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: 1e-05
- train_batch_size: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2618 | 0.5 | 183 | 0.6160 | 0.8727 | 0.8669 |
| 0.2567 | 1.0 | 366 | 0.6154 | 0.8768 | 0.8695 |
| 0.2371 | 1.5 | 549 | 0.6250 | 0.875 | 0.8694 |
| 0.1975 | 2.0 | 732 | 0.6183 | 0.8823 | 0.8772 |
| 0.1882 | 2.5 | 915 | 0.6142 | 0.8837 | 0.8783 |
| 0.1846 | 3.0 | 1098 | 0.6107 | 0.8859 | 0.8805 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1