dwiedarioo/vit-base-patch16-224-in21k-datascience2

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: 0.0109
• Train Accuracy: 0.9997
• Train Top-3-accuracy: 1.0
• Validation Loss: 0.0242
• Validation Accuracy: 0.9948
• Validation Top-3-accuracy: 1.0
• 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: {'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': 2880, '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
0.3365	0.9206	0.9902	0.1057	0.9809	1.0	0
0.0657	0.9891	0.9999	0.0509	0.9902	1.0	1
0.0252	0.9980	1.0	0.0314	0.9945	1.0	2
0.0146	0.9992	1.0	0.0260	0.9948	1.0	3
0.0109	0.9997	1.0	0.0242	0.9948	1.0	4

Framework versions

• Transformers 4.35.0
• TensorFlow 2.14.0
• Datasets 2.14.6
• Tokenizers 0.14.1