metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-vishnu_hwr3
results: []
donut-vishnu_hwr3
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1246
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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0967 | 1.0 | 185 | 0.1919 |
| 0.1843 | 2.0 | 370 | 0.1281 |
| 0.0893 | 3.0 | 555 | 0.1277 |
| 0.1123 | 4.0 | 740 | 0.1331 |
| 0.0158 | 5.0 | 925 | 0.1111 |
| 0.0101 | 6.0 | 1110 | 0.1287 |
| 0.0205 | 7.0 | 1295 | 0.1201 |
| 0.0055 | 8.0 | 1480 | 0.1291 |
| 0.0096 | 9.0 | 1665 | 0.1231 |
| 0.016 | 10.0 | 1850 | 0.1246 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1