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: 0.1309
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: 30
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
No log | 1.0 | 95 | 0.1402 |
0.1888 | 2.0 | 190 | 0.1309 |
0.084 | 3.0 | 285 | 0.1601 |
0.049 | 4.0 | 380 | 0.1853 |
0.0353 | 5.0 | 475 | 0.2052 |
0.0509 | 6.0 | 570 | 0.2052 |
Framework versions
- Transformers 4.37.2
- Pytorch 1.13.1+cu117
- Datasets 2.16.1
- Tokenizers 0.15.1
- Downloads last month
- 9
Unable to determine this model’s pipeline type. Check the
docs
.