segment_50ep

This model is a fine-tuned version of nvidia/mit-b0 on the None dataset. It achieves the following results on the evaluation set:

• eval_loss: 0.0867
• eval_mean_iou: 0.8941
• eval_mean_accuracy: 0.9459
• eval_overall_accuracy: 0.9728
• eval_per_category_iou: [0.8914159628180123, 0.9397057910334902, 0.784713695838044, 0.9606094621573129]
• eval_per_category_accuracy: [0.9685998627316403, 0.9696767617484154, 0.8661740631737143, 0.9789942690602516]
• eval_runtime: 40.9902
• eval_samples_per_second: 0.976
• eval_steps_per_second: 0.244
• epoch: 36.82
• step: 3240

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: 6e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Framework versions

• Transformers 4.26.1
• Pytorch 1.13.0
• Datasets 2.10.1
• Tokenizers 0.13.2