vit-base-newspaper_for_segmetation_classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the Dugerij/newspaper_parser_dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.0104
- Accuracy: 1.0
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: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0429 | 1.0 | 100 | 0.0409 | 0.9929 |
| 0.0159 | 2.0 | 200 | 0.0181 | 1.0 |
| 0.0113 | 3.0 | 300 | 0.0139 | 1.0 |
| 0.0119 | 4.0 | 400 | 0.0112 | 1.0 |
| 0.0093 | 5.0 | 500 | 0.0104 | 1.0 |
Framework versions
- Transformers 4.52.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0