metadata
library_name: transformers
license: mit
base_model: TomasFAV/DonutInvoiceCzechV0R
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: DonutInvoiceCzechV01R
results: []
DonutInvoiceCzechV01R
This model is a fine-tuned version of TomasFAV/DonutInvoiceCzechV0R on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8504
- Accuracy: 0.6633
- F1: 0.6440
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: 9e-05
- train_batch_size: 4
- 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 |
|---|---|---|---|---|---|
| 0.0710 | 1.0 | 150 | 0.6487 | 0.6375 | 0.5855 |
| 0.0373 | 2.0 | 300 | 0.7614 | 0.6007 | 0.5846 |
| 0.0404 | 3.0 | 450 | 0.7921 | 0.6677 | 0.6252 |
| 0.0235 | 4.0 | 600 | 0.8504 | 0.6633 | 0.6440 |
| 0.0251 | 5.0 | 750 | 0.9979 | 0.5279 | 0.5217 |
| 0.0151 | 6.0 | 900 | 0.8938 | 0.6358 | 0.6015 |
| 0.0139 | 7.0 | 1050 | 1.0217 | 0.6184 | 0.5851 |
| 0.0070 | 8.0 | 1200 | 0.9606 | 0.6029 | 0.5794 |
| 0.0010 | 9.0 | 1350 | 0.9824 | 0.6148 | 0.5901 |
| 0.0015 | 10.0 | 1500 | 0.9348 | 0.6272 | 0.5910 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2