segformer_cracks / README.md
Ventalik's picture
End of training
2bd2a9c
|
raw
history blame
1.37 kB
metadata
license: other
base_model: nvidia/mit-b4
tags:
  - generated_from_trainer
model-index:
  - name: segformer_cracks
    results: []

segformer_cracks

This model is a fine-tuned version of nvidia/mit-b4 on the None dataset. It achieves the following results on the evaluation set:

  • eval_loss: 1.3172
  • eval_mean_iou: 0.4811
  • eval_mean_accuracy: 0.5
  • eval_overall_accuracy: 0.9623
  • eval_per_category_iou: [0.962250074678964, 0.0]
  • eval_per_category_accuracy: [1.0, 0.0]
  • eval_runtime: 3654.1653
  • eval_samples_per_second: 0.75
  • eval_steps_per_second: 0.187
  • epoch: 3.0
  • step: 4110

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: 8
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1
  • Datasets 2.14.5
  • Tokenizers 0.13.3