akar49/mri_classifier

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: 0.1032
• Validation Loss: 0.1556
• Train Accuracy: 0.9367
• Epoch: 14

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': 'SGD', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': 0.001, 'momentum': 0.0, 'nesterov': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
0.6447	0.6133	0.7004	0
0.5405	0.5010	0.8256	1
0.4181	0.3917	0.8650	2
0.3122	0.3189	0.9058	3
0.2474	0.3069	0.8875	4
0.2021	0.2733	0.9044	5
0.1745	0.2455	0.9100	6
0.1591	0.2203	0.9212	7
0.1450	0.2350	0.9142	8
0.1397	0.2122	0.9198	9
0.1227	0.2098	0.9212	10
0.1169	0.1754	0.9325	11
0.1080	0.1782	0.9339	12
0.0971	0.1705	0.9353	13
0.1032	0.1556	0.9367	14

Framework versions

• Transformers 4.30.2
• TensorFlow 2.12.0
• Datasets 2.13.1
• Tokenizers 0.13.3