djibri/mri_classifier

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

• Train Loss: 0.7116
• Validation Loss: 0.7235
• Train Accuracy: 0.6880
• Epoch: 19

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': 'Adam', '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, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Train Accuracy	Epoch
1.1610	0.9961	0.5301	0
1.0175	1.0906	0.5408	1
0.9817	1.1593	0.5324	2
0.9390	0.9281	0.5957	3
0.8854	0.9142	0.5934	4
0.8572	0.8900	0.5652	5
0.8584	0.8369	0.6056	6
0.8174	0.8710	0.5812	7
0.8190	0.8142	0.6209	8
0.7977	0.8600	0.5774	9
0.8046	0.8344	0.5988	10
0.7905	0.7853	0.6568	11
0.7773	0.9653	0.5728	12
0.7825	0.7865	0.6217	13
0.7833	0.8118	0.6575	14
0.7693	0.8081	0.6484	15
0.7503	0.7707	0.6690	16
0.7425	0.7434	0.6903	17
0.7700	0.7249	0.7109	18
0.7116	0.7235	0.6880	19

Framework versions

• Transformers 4.47.0
• TensorFlow 2.17.1
• Datasets 3.3.1
• Tokenizers 0.21.0