| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/pix2struct-textcaps-base |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - f1 |
| model-index: |
| - name: Pix2StructCzechInvoiceV0R |
| 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. --> |
|
|
| # Pix2StructCzechInvoiceV0R |
|
|
| This model is a fine-tuned version of [google/pix2struct-textcaps-base](https://huggingface.co/google/pix2struct-textcaps-base) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3507 |
| - Accuracy: 0.7117 |
| - F1: 0.4741 |
|
|
| ## 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: 1 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - num_epochs: 10 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
| | 2.3226 | 1.0 | 150 | 2.3375 | 0.0117 | 0.0 | |
| | 0.9378 | 2.0 | 300 | 1.0392 | 0.0289 | 0.0 | |
| | 0.7639 | 3.0 | 450 | 0.9131 | 0.0 | 0.0 | |
| | 0.5096 | 4.0 | 600 | 0.6851 | 0.5907 | 0.4268 | |
| | 0.2828 | 5.0 | 750 | 0.4679 | 0.6683 | 0.4740 | |
| | 0.1613 | 6.0 | 900 | 0.3983 | 0.0 | 0.0 | |
| | 0.0946 | 7.0 | 1050 | 0.3642 | 0.0 | 0.0 | |
| | 0.0693 | 8.0 | 1200 | 0.3507 | 0.7117 | 0.4741 | |
| | 0.0590 | 9.0 | 1350 | 0.3610 | 0.7013 | 0.4578 | |
| | 0.0498 | 10.0 | 1500 | 0.3624 | 0.0 | 0.0 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.0.0 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
| |
