---
library_name: transformers
license: apache-2.0
base_model: facebook/convnext-base-224-22k
tags:
- image-classification
- vision
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Validated_cracks_raw_dataset_359_convnext_model
  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. -->

# Validated_cracks_raw_dataset_359_convnext_model

This model is a fine-tuned version of [facebook/convnext-base-224-22k](https://huggingface.co/facebook/convnext-base-224-22k) on the Logiroad/Validated_cracks_raw_dataset_359 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.0441
- Accuracy: 0.6021

## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 30.0
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.05

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.3724        | 1.0   | 108  | 1.3690          | 0.3134   |
| 1.3528        | 2.0   | 216  | 1.3015          | 0.4014   |
| 1.2839        | 3.0   | 324  | 1.2375          | 0.4331   |
| 1.2608        | 4.0   | 432  | 1.1975          | 0.4930   |
| 1.2178        | 5.0   | 540  | 1.1368          | 0.5246   |
| 1.1624        | 6.0   | 648  | 1.1164          | 0.4965   |
| 1.1108        | 7.0   | 756  | 1.1063          | 0.5282   |
| 1.1028        | 8.0   | 864  | 1.1174          | 0.5317   |
| 1.1023        | 9.0   | 972  | 1.1123          | 0.5458   |
| 1.0572        | 10.0  | 1080 | 1.0755          | 0.5739   |
| 0.9874        | 11.0  | 1188 | 1.0952          | 0.5599   |
| 1.0132        | 12.0  | 1296 | 1.0767          | 0.5775   |
| 0.9898        | 13.0  | 1404 | 1.0616          | 0.5880   |
| 1.0182        | 14.0  | 1512 | 1.0420          | 0.5810   |
| 0.9889        | 15.0  | 1620 | 1.0441          | 0.6021   |
| 0.9446        | 16.0  | 1728 | 1.0512          | 0.6021   |
| 0.9519        | 17.0  | 1836 | 1.0737          | 0.5704   |
| 0.9458        | 18.0  | 1944 | 1.0471          | 0.5669   |
| 0.9347        | 19.0  | 2052 | 1.0513          | 0.5845   |
| 0.8863        | 20.0  | 2160 | 1.0428          | 0.5951   |
| 0.8507        | 21.0  | 2268 | 1.0527          | 0.5951   |
| 0.8712        | 22.0  | 2376 | 1.0560          | 0.5915   |
| 0.8857        | 23.0  | 2484 | 1.0447          | 0.5880   |
| 0.8848        | 24.0  | 2592 | 1.0512          | 0.5951   |
| 0.904         | 25.0  | 2700 | 1.0513          | 0.5845   |
| 0.943         | 26.0  | 2808 | 1.0480          | 0.5880   |
| 0.862         | 27.0  | 2916 | 1.0476          | 0.5880   |
| 0.864         | 28.0  | 3024 | 1.0469          | 0.5880   |
| 0.8879        | 29.0  | 3132 | 1.0468          | 0.5880   |
| 0.8099        | 30.0  | 3240 | 1.0468          | 0.5880   |


### Framework versions

- Transformers 4.46.1
- Pytorch 2.3.0
- Datasets 3.1.0
- Tokenizers 0.20.3