donut-stnk-v5_3_2-left
This model is a fine-tuned version of philschmid/donut-base-sroie on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0767
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 |
---|---|---|---|
0.179 | 1.0 | 215 | 0.0998 |
0.0773 | 2.0 | 430 | 0.0825 |
0.066 | 3.0 | 645 | 0.0799 |
0.0461 | 4.0 | 860 | 0.0802 |
0.023 | 5.0 | 1075 | 0.0767 |
0.0165 | 6.0 | 1290 | 0.0834 |
0.0155 | 7.0 | 1505 | 0.0851 |
0.0079 | 8.0 | 1720 | 0.0807 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 1
Unable to determine this model’s pipeline type. Check the
docs
.