greathero/mit-b0-finetuned-contrails-morethanx33newercontrailsdataset

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

• Train Loss: 0.1577
• Validation Loss: 0.1651
• Validation Mean Iou: 0.2490
• Validation Mean Accuracy: 0.25
• Validation Overall Accuracy: 0.9958
• Validation Accuracy Unlabeled: 0.0
• Validation Accuracy Notlabeled: 1.0
• Validation Accuracy Otherclass: 0.0
• Validation Accuracy Contrail: 0.0
• Validation Iou Unlabeled: 0.0
• Validation Iou Notlabeled: 0.9958
• Validation Iou Otherclass: 0.0
• Validation Iou Contrail: 0.0
• Epoch: 3

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': 6e-05, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
• training_precision: float32

Training results

Train Loss	Validation Loss	Validation Mean Iou	Validation Mean Accuracy	Validation Overall Accuracy	Validation Accuracy Unlabeled	Validation Accuracy Notlabeled	Validation Accuracy Otherclass	Validation Accuracy Contrail	Validation Iou Unlabeled	Validation Iou Notlabeled	Validation Iou Otherclass	Validation Iou Contrail	Epoch
1.4224	1.3413	0.0440	0.2777	0.1745	0.0	0.1713	0.0	0.9395	0.0	0.1713	0.0	0.0047	0
0.5445	0.5276	0.2436	0.2466	0.9726	0.0	0.9766	0.0	0.0097	0.0	0.9726	0.0	0.0016	1
0.2702	0.2208	0.2489	0.2516	0.9896	0.0	0.9936	0.0	0.0126	0.0	0.9896	0.0	0.0060	2
0.1577	0.1651	0.2490	0.25	0.9958	0.0	1.0	0.0	0.0	0.0	0.9958	0.0	0.0	3

Framework versions

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