Segformer-MRIseg_model_Dec28

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: 0.0035
• Validation Loss: 0.0096
• 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
0.1321	0.0670	0
0.0670	0.0541	1
0.0551	0.0481	2
0.0455	0.0458	3
0.0393	0.0377	4
0.0335	0.0329	5
0.0316	0.0322	6
0.0269	0.0255	7
0.0218	0.0249	8
0.0204	0.0187	9
0.0182	0.0231	10
0.0186	0.0244	11
0.0166	0.0175	12
0.0150	0.0157	13
0.0132	0.0163	14
0.0123	0.0161	15
0.0111	0.0147	16
0.0112	0.0231	17
0.0122	0.0145	18
0.0101	0.0134	19
0.0094	0.0122	20
0.0088	0.0117	21
0.0080	0.0128	22
0.0082	0.0140	23
0.0074	0.0125	24
0.0073	0.0110	25
0.0071	0.0107	26
0.0065	0.0111	27
0.0073	0.0109	28
0.0068	0.0104	29
0.0064	0.0100	30
0.0062	0.0098	31
0.0065	0.0112	32
0.0064	0.0107	33
0.0059	0.0105	34
0.0065	0.0107	35
0.0058	0.0100	36
0.0052	0.0099	37
0.0052	0.0107	38
0.0055	0.0123	39
0.0052	0.0097	40
0.0051	0.0101	41
0.0051	0.0102	42
0.0046	0.0105	43
0.0048	0.0093	44
0.0044	0.0096	45
0.0043	0.0094	46
0.0040	0.0119	47
0.0041	0.0110	48
0.0043	0.0095	49
0.0041	0.0099	50
0.0040	0.0097	51
0.0041	0.0098	52
0.0041	0.0097	53
0.0041	0.0094	54
0.0042	0.0097	55
0.0038	0.0101	56
0.0037	0.0096	57
0.0036	0.0096	58
0.0035	0.0096	59

Framework versions

• Transformers 4.35.2
• TensorFlow 2.15.0
• Datasets 2.16.0
• Tokenizers 0.15.0