Segformer-MRIseg_model_Mar24

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: 0.0037
• Validation Loss: 0.0081
• 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
0.5861	0.0929	0
0.0953	0.0606	1
0.0509	0.0350	2
0.0308	0.0231	3
0.0253	0.0219	4
0.0202	0.0179	5
0.0162	0.0184	6
0.0152	0.0188	7
0.0135	0.0157	8
0.0119	0.0170	9
0.0110	0.0150	10
0.0102	0.0157	11
0.0097	0.0137	12
0.0095	0.0141	13
0.0087	0.0118	14
0.0079	0.0116	15
0.0075	0.0119	16
0.0072	0.0109	17
0.0069	0.0118	18
0.0068	0.0104	19
0.0065	0.0108	20
0.0064	0.0124	21
0.0062	0.0095	22
0.0058	0.0111	23
0.0058	0.0094	24
0.0056	0.0111	25
0.0055	0.0125	26
0.0057	0.0104	27
0.0053	0.0096	28
0.0051	0.0105	29
0.0050	0.0103	30
0.0048	0.0091	31
0.0047	0.0097	32
0.0044	0.0094	33
0.0045	0.0092	34
0.0045	0.0093	35
0.0047	0.0088	36
0.0048	0.0089	37
0.0045	0.0108	38
0.0043	0.0088	39
0.0043	0.0090	40
0.0044	0.0106	41
0.0053	0.0100	42
0.0051	0.0102	43
0.0044	0.0097	44
0.0039	0.0088	45
0.0040	0.0097	46
0.0040	0.0089	47
0.0037	0.0095	48
0.0034	0.0085	49
0.0041	0.0082	50
0.0054	0.0098	51
0.0053	0.0085	52
0.0044	0.0086	53
0.0040	0.0082	54
0.0038	0.0082	55
0.0035	0.0092	56
0.0034	0.0090	57
0.0035	0.0079	58
0.0037	0.0081	59

Framework versions

• Transformers 4.38.1
• TensorFlow 2.15.0
• Datasets 2.18.0
• Tokenizers 0.15.2