metadata
library_name: transformers
license: cc-by-nc-sa-4.0
base_model: microsoft/layoutlmv3-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: layoutlmv3-ap8_2_stitched_8_batch_4e5
results: []
layoutlmv3-ap8_2_stitched_8_batch_4e5
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: 0.1770
- Precision: 1.0
- Recall: 0.0291
- F1: 0.0566
- Accuracy: 0.9795
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: 4e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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: 0.1
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.4099 | 16.6667 | 250 | 0.1770 | 1.0 | 0.0291 | 0.0566 | 0.9795 |
| 0.0277 | 33.3333 | 500 | 0.2041 | 0.1739 | 0.0388 | 0.0635 | 0.9787 |
| 0.0059 | 50.0 | 750 | 0.2190 | 0.3 | 0.0874 | 0.1353 | 0.9782 |
| 0.0033 | 66.6667 | 1000 | 0.2216 | 0.1923 | 0.0485 | 0.0775 | 0.9783 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1