metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut_marriage_ms_420-105_001
results: []
donut_marriage_ms_420-105_001
This model is a fine-tuned version of naver-clova-ix/donut-base on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3288
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: 2
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 150
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.8064 | 1.0 | 210 | 0.4931 |
| 0.2443 | 2.0 | 420 | 0.3622 |
| 0.0773 | 3.0 | 630 | 0.2789 |
| 0.171 | 4.0 | 840 | 0.2603 |
| 0.1889 | 5.0 | 1050 | 0.2761 |
| 0.0565 | 6.0 | 1260 | 0.3071 |
| 0.0226 | 7.0 | 1470 | 0.2881 |
| 0.1198 | 8.0 | 1680 | 0.3040 |
| 0.0093 | 9.0 | 1890 | 0.3188 |
| 0.0049 | 10.0 | 2100 | 0.3357 |
| 0.0275 | 11.0 | 2310 | 0.3541 |
| 0.0198 | 12.0 | 2520 | 0.3420 |
| 0.0306 | 13.0 | 2730 | 0.3330 |
| 0.0874 | 14.0 | 2940 | 0.3288 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.1+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0