vit-base-patch16-224-in21k-rock360 – AI Model by jayashprasad | AlphaNeural AI

You can deploy this model and start earning money today!

jayashprasad/
vit-base-patch16-224-in21k-rock360

like

0

image-classification

generated_from_keras_callback

google/vit-base-patch16-224-in21k

autotrain_compatible

endpoints_compatible

Views

No views yet

jayashprasad/vit-base-patch16-224-in21k-rock360

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on Rock 360 dataset. It achieves the following results on the evaluation set:

Train Loss: 0.4089
Train Accuracy: 0.9875
Validation Loss: 0.7470
Validation Accuracy: 0.7250
Epoch: 7

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': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 160, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
training_precision: mixed_float16

Training results

Train Loss	Train Accuracy	Validation Loss	Validation Accuracy	Epoch
1.0814	0.4417	1.0415	0.5917	0
0.9565	0.7917	0.9933	0.6667	1
0.8566	0.8542	0.9488	0.6833	2
0.7581	0.9208	0.9017	0.6833	3
0.6599	0.9500	0.8592	0.7250	4
0.5664	0.9667	0.8179	0.7083	5
0.4843	0.9833	0.7797	0.7333	6
0.4089	0.9875	0.7470	0.7250	7

Framework versions

Transformers 4.35.2
TensorFlow 2.10.1
Datasets 2.15.0
Tokenizers 0.15.0