metadata

license: other
base_model: nvidia/segformer-b0-finetuned-ade-512-512
tags:
  - generated_from_keras_callback
model-index:
  - name: segformer-b0-finetuned-deprem-satellite
    results: []

segformer-b0-finetuned-deprem-satellite

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: 0.0405
Validation Loss: 0.0344
Epoch: 49

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': 5e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
0.1619	0.0524	0
0.0943	0.0437	1
0.0811	0.0402	2
0.0756	0.0390	3
0.0714	0.0365	4
0.0676	0.0367	5
0.0648	0.0361	6
0.0627	0.0352	7
0.0617	0.0423	8
0.0597	0.0348	9
0.0582	0.0338	10
0.0575	0.0340	11
0.0553	0.0338	12
0.0551	0.0328	13
0.0542	0.0353	14
0.0541	0.0348	15
0.0526	0.0325	16
0.0512	0.0326	17
0.0511	0.0338	18
0.0506	0.0338	19
0.0501	0.0326	20
0.0488	0.0339	21
0.0488	0.0329	22
0.0481	0.0335	23
0.0475	0.0327	24
0.0469	0.0335	25
0.0463	0.0331	26
0.0478	0.0326	27
0.0455	0.0331	28
0.0511	0.0328	29
0.0454	0.0327	30
0.0447	0.0330	31
0.0466	0.0341	32
0.0445	0.0331	33
0.0441	0.0333	34
0.0438	0.0337	35
0.0441	0.0347	36
0.0463	0.0334	37
0.0446	0.0336	38
0.0430	0.0337	39
0.0425	0.0342	40
0.0422	0.0339	41
0.0426	0.0348	42
0.0418	0.0339	43
0.0416	0.0339	44
0.0414	0.0343	45
0.0423	0.0337	46
0.0408	0.0353	47
0.0405	0.0343	48
0.0405	0.0344	49

Framework versions

Transformers 4.36.2
TensorFlow 2.15.0
Datasets 2.16.1
Tokenizers 0.15.0