metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: output_dir-full_dataset
results: []
output_dir-full_dataset
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2097
- Accuracy: 0.9170
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: 0.0002
- train_batch_size: 10
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1689 | 1.0 | 2916 | 1.5921 | 0.3398 |
| 0.5282 | 2.0 | 5832 | 0.4584 | 0.8296 |
| 0.2224 | 3.0 | 8748 | 0.2097 | 0.9170 |
Framework versions
- Transformers 4.39.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2