metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-base-sroie
results: []
donut-base-sroie
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.5314
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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6691 | 1.0 | 69 | 1.4307 |
| 1.2955 | 2.0 | 138 | 1.4857 |
| 0.3205 | 3.0 | 207 | 1.4528 |
| 0.4622 | 4.0 | 276 | 1.3993 |
| 0.8009 | 5.0 | 345 | 1.4648 |
| 1.1553 | 6.0 | 414 | 1.4508 |
| 0.6056 | 7.0 | 483 | 1.4568 |
| 0.1881 | 8.0 | 552 | 1.4941 |
| 0.7731 | 9.0 | 621 | 1.5314 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1