---
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: lettuce-npk-vit
  results:
  - task:
      name: Image Classification
      type: image-classification
    dataset:
      name: imagefolder
      type: imagefolder
      config: default
      split: train
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8095238095238095
---

<!-- 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. -->

[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/abdoulaye-diop/lettuce-npk-deficiency-prediction/runs/at88jlqw)
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/abdoulaye-diop/lettuce-npk-deficiency-prediction/runs/at88jlqw)
# lettuce-npk-vit

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7449
- Accuracy: 0.8095

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20

### Training results

| Training Loss | Epoch   | Step | Validation Loss | Accuracy |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
| No log        | 0.7273  | 2    | 1.3774          | 0.2143   |
| No log        | 1.8182  | 5    | 1.2738          | 0.4524   |
| No log        | 2.9091  | 8    | 1.1874          | 0.6190   |
| 1.2511        | 4.0     | 11   | 1.1162          | 0.7619   |
| 1.2511        | 4.7273  | 13   | 1.0780          | 0.7143   |
| 1.2511        | 5.8182  | 16   | 1.0037          | 0.7857   |
| 1.2511        | 6.9091  | 19   | 0.9342          | 0.8095   |
| 0.9308        | 8.0     | 22   | 0.8653          | 0.8095   |
| 0.9308        | 8.7273  | 24   | 0.8485          | 0.8095   |
| 0.9308        | 9.8182  | 27   | 0.8264          | 0.8333   |
| 0.7204        | 10.9091 | 30   | 0.8243          | 0.7857   |
| 0.7204        | 12.0    | 33   | 0.7299          | 0.8571   |
| 0.7204        | 12.7273 | 35   | 0.7376          | 0.8095   |
| 0.7204        | 13.8182 | 38   | 0.7358          | 0.8333   |
| 0.6101        | 14.5455 | 40   | 0.7449          | 0.8095   |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1