akar49/MRI_segmentation-1

This model is a fine-tuned version of nvidia/segformer-b0-finetuned-ade-512-512 on an unknown dataset. It achieves the following results on the evaluation set:

• Train Loss: 0.0034
• Validation Loss: 0.0098
• Epoch: 59

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	Epoch
0.3300	0.0731	0
0.0881	0.0651	1
0.0660	0.0632	2
0.0573	0.0463	3
0.0525	0.0495	4
0.0475	0.0431	5
0.0379	0.0367	6
0.0318	0.0319	7
0.0280	0.0260	8
0.0246	0.0253	9
0.0235	0.0267	10
0.0205	0.0205	11
0.0182	0.0227	12
0.0182	0.0234	13
0.0169	0.0197	14
0.0163	0.0200	15
0.0173	0.0192	16
0.0130	0.0179	17
0.0123	0.0123	18
0.0103	0.0137	19
0.0098	0.0121	20
0.0114	0.0115	21
0.0097	0.0116	22
0.0083	0.0108	23
0.0078	0.0116	24
0.0074	0.0102	25
0.0071	0.0121	26
0.0073	0.0104	27
0.0071	0.0128	28
0.0066	0.0110	29
0.0061	0.0103	30
0.0067	0.0115	31
0.0071	0.0246	32
0.0091	0.0106	33
0.0079	0.0107	34
0.0066	0.0109	35
0.0059	0.0104	36
0.0057	0.0092	37
0.0055	0.0096	38
0.0052	0.0099	39
0.0051	0.0102	40
0.0057	0.0108	41
0.0049	0.0097	42
0.0048	0.0093	43
0.0047	0.0095	44
0.0045	0.0115	45
0.0047	0.0114	46
0.0048	0.0105	47
0.0049	0.0093	48
0.0050	0.0093	49
0.0044	0.0097	50
0.0040	0.0101	51
0.0041	0.0098	52
0.0041	0.0099	53
0.0039	0.0109	54
0.0040	0.0099	55
0.0038	0.0112	56
0.0037	0.0096	57
0.0035	0.0106	58
0.0034	0.0098	59

Framework versions

• Transformers 4.31.0
• TensorFlow 2.12.0
• Datasets 2.14.2
• Tokenizers 0.13.3