893_Images_Json
This model is a fine-tuned version of naver-clova-ix/donut-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4844
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: 2e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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
- lr_scheduler_warmup_steps: 100
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 13.6598 | 1.0754 | 200 | 2.7064 |
| 6.6749 | 2.1507 | 400 | 1.5175 |
| 3.6877 | 3.2261 | 600 | 0.8923 |
| 2.1001 | 4.3015 | 800 | 0.6686 |
| 1.6768 | 5.3769 | 1000 | 0.5783 |
| 1.3900 | 6.4522 | 1200 | 0.5409 |
| 1.1434 | 7.5276 | 1400 | 0.5079 |
| 0.9839 | 8.6030 | 1600 | 0.5004 |
| 0.8089 | 9.6783 | 1800 | 0.4942 |
| 0.7735 | 10.7537 | 2000 | 0.4867 |
| 0.7466 | 11.8291 | 2200 | 0.4888 |
| 0.7352 | 12.9044 | 2400 | 0.4861 |
| 0.6183 | 13.9798 | 2600 | 0.4840 |
| 0.5964 | 15.0 | 2790 | 0.4844 |
Framework versions
- Transformers 5.10.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2