segformer-test

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: 0.3699
• eval_mean_iou: 0.5261
• eval_mean_accuracy: 0.6103
• eval_overall_accuracy: 0.9163
• eval_per_category_iou: [0.6440921586675343, 0.7803556002366734, 0.2939456425332648, 0.21142047034966666, 0.38076799132467504, 0.517520127105597, 0.8584623722607826, 0.9583354624978893, 0.1412645399055626, 0.12232558139534884, 0.8788054295225798, nan]
• eval_per_category_accuracy: [0.8187515502058933, 0.9113968634790757, 0.31292325038191526, 0.24646864879791802, 0.4941417789077488, 0.6124207890888539, 0.9331841161885152, 0.9812724610884527, 0.17548427708947323, 0.2838640043173233, 0.9429806974946743, nan]
• eval_runtime: 344.8194
• eval_samples_per_second: 1.351
• eval_steps_per_second: 0.676
• epoch: 6.16
• step: 6760

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: 2
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.17.1
• Tokenizers 0.15.2