metadata
base_model: squantumengine/donut-stnk-v4_mid
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: donut-stnk-v5-mid-with-location-code
results: []
donut-stnk-v5-mid-with-location-code
This model is a fine-tuned version of squantumengine/donut-stnk-v4_mid on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1469
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 |
|---|---|---|---|
| No log | 1.0 | 95 | 0.1490 |
| 0.196 | 2.0 | 190 | 0.1486 |
| 0.0822 | 3.0 | 285 | 0.1469 |
| 0.0438 | 4.0 | 380 | 0.1736 |
| 0.0256 | 5.0 | 475 | 0.1507 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1