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

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: 0.2848
• Train Accuracy: 0.9969
• Train Top-3-accuracy: 0.9992
• Validation Loss: 0.3786
• Validation Accuracy: 0.9590
• Validation Top-3-accuracy: 0.9892
• 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': {'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': 1230, '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
2.2199	0.4215	0.6564	1.8634	0.5702	0.8099	0
1.5448	0.6976	0.8797	1.3110	0.7603	0.9028	1
1.0494	0.8694	0.9519	0.9507	0.8855	0.9590	2
0.7408	0.9381	0.9824	0.7499	0.9114	0.9806	3
0.5428	0.9756	0.9939	0.5831	0.9460	0.9849	4
0.4169	0.9901	0.9977	0.4895	0.9525	0.9914	5
0.3371	0.9947	0.9977	0.4194	0.9611	0.9892	6
0.2848	0.9969	0.9992	0.3786	0.9590	0.9892	7

Framework versions

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