metadata
license: mit
base_model: naver-clova-ix/donut-base
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-donut_hwr
results: []
donut-base-donut_hwr
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: 0.2801
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 |
|---|---|---|---|
| 3.4951 | 1.0 | 63 | 2.6379 |
| 1.8703 | 2.0 | 126 | 0.9333 |
| 0.6529 | 3.0 | 189 | 0.4541 |
| 0.3478 | 4.0 | 252 | 0.3967 |
| 0.2653 | 5.0 | 315 | 0.3254 |
| 0.1697 | 6.0 | 378 | 0.3221 |
| 0.3587 | 7.0 | 441 | 0.3045 |
| 0.2229 | 8.0 | 504 | 0.2994 |
| 0.1948 | 9.0 | 567 | 0.2825 |
| 0.1457 | 10.0 | 630 | 0.2801 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1