deprem_satellite_semantic_xview2_large_2

This model is a fine-tuned version of nvidia/mit-b5 on an unknown dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.9892
• eval_mean_iou: 0.3093
• eval_mean_accuracy: 0.3576
• eval_overall_accuracy: 0.9646
• eval_accuracy_background: 0.9860
• eval_accuracy_nodamage: 0.8022
• eval_accuracy_minordamaged: 0.0
• eval_accuracy_majordamaged: 0.0
• eval_accuracy_destroyed: 0.0
• eval_iou_background: 0.9677
• eval_iou_nodamage: 0.5789
• eval_iou_minordamaged: 0.0
• eval_iou_majordamaged: 0.0
• eval_iou_destroyed: 0.0
• eval_runtime: 200.8095
• eval_samples_per_second: 4.646
• eval_steps_per_second: 4.646
• epoch: 19.3
• step: 27000

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:

• learning_rate: 0.0001
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 2
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Framework versions

• Transformers 4.27.0.dev0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2