metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- vision
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: image_segmentation_classifier
results: []
image_segmentation_classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the taresco/newspaper_ocr dataset. It achieves the following results on the evaluation set:
- Loss: 0.0033
- Accuracy: 0.9993
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 |
|---|---|---|---|---|
| 0.0014 | 1.0 | 2031 | 0.0065 | 0.9986 |
| 0.0005 | 2.0 | 4062 | 0.0033 | 0.9993 |
| 0.0003 | 3.0 | 6093 | 0.0058 | 0.9990 |
| 0.0002 | 4.0 | 8124 | 0.0043 | 0.9983 |
| 0.0001 | 5.0 | 10155 | 0.0036 | 0.9990 |
Framework versions
- Transformers 4.52.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0