metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- image-classification
- tensorflow
- vision
- generated_from_keras_callback
model-index:
- name: RenSurii/vit-base-patch16-224-in21k-finetuned-image-classification
results: []
RenSurii/vit-base-patch16-224-in21k-finetuned-image-classification
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the mnist dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.3712
- Train Accuracy: 0.9621
- Validation Loss: 0.3312
- Validation Accuracy: 0.9621
- Epoch: 5
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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': 1.0, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 6000, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 2.0107 | 0.8548 | 1.5288 | 0.8548 | 0 |
| 1.3538 | 0.9149 | 0.9913 | 0.9149 | 1 |
| 0.9517 | 0.934 | 0.7421 | 0.9340 | 2 |
| 0.6882 | 0.9467 | 0.5690 | 0.9467 | 3 |
| 0.4999 | 0.9554 | 0.4264 | 0.9554 | 4 |
| 0.3712 | 0.9621 | 0.3312 | 0.9621 | 5 |
Framework versions
- Transformers 4.47.0.dev0
- TensorFlow 2.18.0
- Datasets 3.1.0
- Tokenizers 0.20.3