donut_synDB
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: 0.0953
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: 3
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.1842 | 0.62 | 160 | 0.1902 |
0.0935 | 0.92 | 240 | 0.1581 |
0.0489 | 1.23 | 320 | 0.1757 |
0.042 | 1.54 | 400 | 0.1167 |
0.0276 | 1.85 | 480 | 0.1258 |
0.0283 | 2.15 | 560 | 0.1575 |
0.0164 | 2.46 | 640 | 0.1349 |
0.0146 | 2.77 | 720 | 0.1525 |
0.0216 | 3.08 | 800 | 0.1560 |
0.0125 | 3.38 | 880 | 0.0761 |
0.0118 | 3.69 | 960 | 0.1530 |
0.0106 | 4.0 | 1040 | 0.0679 |
0.01 | 4.31 | 1120 | 0.1074 |
0.0086 | 4.62 | 1200 | 0.0802 |
0.0104 | 4.92 | 1280 | 0.0723 |
0.0108 | 5.23 | 1360 | 0.0780 |
0.0093 | 5.54 | 1440 | 0.0896 |
0.0051 | 5.85 | 1520 | 0.1106 |
0.0116 | 6.15 | 1600 | 0.0895 |
0.0043 | 6.46 | 1680 | 0.0919 |
0.0074 | 6.77 | 1760 | 0.0953 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 9
Unable to determine this model’s pipeline type. Check the
docs
.