You can deploy this model and start earning money today!

suryanshgoel/
vit-base-patch16-224-in21k-euroSat

Name: vit-base-patch16-224-in21k-euroSat
Availability: InStock

generated_from_keras_callback

google/vit-base-patch16-224-in21k

Views

No views yet

suryanshgoel/vit-base-patch16-224-in21k-euroSat

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: 0.5270
Train Accuracy: 0.9965
Train Top-3-accuracy: 0.9990
Validation Loss: 1.2029
Validation Accuracy: 0.7352
Validation Top-3-accuracy: 0.9352
Epoch: 9

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: {'inner_optimizer': {'module': 'transformers.optimization_tf', 'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 6300, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.8999999761581421, 'beta_2': 0.9990000128746033, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}, 'registered_name': 'AdamWeightDecay'}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
training_precision: mixed_float16

Training results

Train Loss	Train Accuracy	Train Top-3-accuracy	Validation Loss	Validation Accuracy	Validation Top-3-accuracy	Epoch
3.1420	0.3167	0.5274	2.9076	0.4394	0.6958	0
2.6104	0.5642	0.8297	2.4594	0.5577	0.8282	1
2.1588	0.6783	0.9168	2.1385	0.6225	0.8789	2
1.7981	0.7689	0.9612	1.8776	0.6732	0.9042	3
1.4937	0.8381	0.9816	1.6875	0.6958	0.9014	4
1.2306	0.8979	0.9910	1.5326	0.7211	0.9211	5
1.0046	0.9377	0.9940	1.4043	0.7183	0.9296	6
0.8088	0.9731	0.9975	1.3022	0.7408	0.9268	7
0.6470	0.9905	0.9980	1.2706	0.7352	0.9296	8
0.5270	0.9965	0.9990	1.2029	0.7352	0.9352	9

Framework versions

Transformers 4.32.1
TensorFlow 2.15.0
Datasets 2.12.0
Tokenizers 0.13.3