---
license: other
base_model: nvidia/mit-b3
tags:
- generated_from_trainer
model-index:
- name: segformer_cracks_v2
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# segformer_cracks_v2

This model is a fine-tuned version of [nvidia/mit-b3](https://huggingface.co/nvidia/mit-b3) on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.0537
- eval_mean_iou: 0.7604
- eval_mean_accuracy: 0.8281
- eval_overall_accuracy: 0.9788
- eval_per_category_iou: [0.9782807410260149, 0.5424475354128461]
- eval_per_category_accuracy: [0.9911386477455301, 0.6649739140722758]
- eval_runtime: 1877.8784
- eval_samples_per_second: 1.459
- eval_steps_per_second: 0.365
- epoch: 1.0
- step: 1370

## 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