Alph0nse/vit-base-patch16-224-in21k_v2_breed_cls_v2

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.8190
• Train Accuracy: 0.9248
• Train Top-3-accuracy: 0.9777
• Validation Loss: 0.9820
• Validation Accuracy: 0.9308
• Validation Top-3-accuracy: 0.9799
• Epoch: 4

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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 560, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
2.4175	0.5263	0.7190	1.9955	0.7702	0.9039	0
1.5487	0.8270	0.9344	1.4502	0.8624	0.9519	1
1.1223	0.8829	0.9609	1.1583	0.8982	0.9674	2
0.9127	0.9094	0.9718	1.0461	0.9181	0.9753	3
0.8190	0.9248	0.9777	0.9820	0.9308	0.9799	4

Framework versions

• Transformers 4.38.2
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2