ahmed-ai/mit-b1-skin-lesion-classifier

ahmed-ai/mit-b1-skin-classifier

Important Warning

This model is currently undergoing development; as such, it should not be used for clinical diagnosis or relied upon for medical decision-making at this stage.

This model is a fine-tuned version of nvidia/mit-b1 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.4567
• Validation Loss: 0.6271
• Train Accuracy: 0.7610
• 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: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 191770, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
1.1152	0.8715	0.6858	0
0.8784	0.7400	0.7216	1
0.7774	0.7492	0.7273	2
0.7114	0.7229	0.7213	3
0.6492	0.6735	0.7393	4
0.6005	0.6498	0.7507	5
0.5560	0.6181	0.7596	6
0.5179	0.6473	0.7582	7
0.4913	0.6100	0.7711	8
0.4567	0.6271	0.7610	9

Framework versions

• Transformers 4.36.2
• TensorFlow 2.13.0
• Datasets 2.16.1
• Tokenizers 0.15.0