donut_synDB_plusv6_2
This model is a fine-tuned version of Donut01/donut_synDB_plusv6 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0420
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 10
- total_train_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.0557 | 1.0 | 20 | 0.0677 |
0.0486 | 1.5 | 30 | 0.0602 |
0.039 | 2.0 | 40 | 0.0491 |
0.035 | 2.5 | 50 | 0.0445 |
0.0316 | 3.0 | 60 | 0.0411 |
0.0336 | 3.5 | 70 | 0.0406 |
0.0426 | 4.0 | 80 | 0.0415 |
0.0457 | 4.5 | 90 | 0.0422 |
0.0504 | 5.0 | 100 | 0.0420 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 14
Unable to determine this model’s pipeline type. Check the
docs
.