---
library_name: transformers
license: apache-2.0
base_model: google/vit-hybrid-base-bit-384
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-hybrid-base-bit-384_rice-leaf-disease-augmented-v2_fft
  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. -->

# vit-hybrid-base-bit-384_rice-leaf-disease-augmented-v2_fft

This model is a fine-tuned version of [google/vit-hybrid-base-bit-384](https://huggingface.co/google/vit-hybrid-base-bit-384) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3756
- Accuracy: 0.9286

## 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: 32
- eval_batch_size: 32
- seed: 42
- 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_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 1.203         | 1.0   | 250  | 0.4459          | 0.8512   |
| 0.1159        | 2.0   | 500  | 0.3121          | 0.9077   |
| 0.0136        | 3.0   | 750  | 0.3433          | 0.9226   |
| 0.001         | 4.0   | 1000 | 0.3377          | 0.9226   |
| 0.0003        | 5.0   | 1250 | 0.3365          | 0.9226   |
| 0.0002        | 6.0   | 1500 | 0.3366          | 0.9286   |
| 0.0002        | 7.0   | 1750 | 0.3432          | 0.9286   |
| 0.0001        | 8.0   | 2000 | 0.3478          | 0.9286   |
| 0.0001        | 9.0   | 2250 | 0.3530          | 0.9286   |
| 0.0001        | 10.0  | 2500 | 0.3543          | 0.9286   |
| 0.0001        | 11.0  | 2750 | 0.3592          | 0.9286   |
| 0.0           | 12.0  | 3000 | 0.3698          | 0.9286   |
| 0.0           | 13.0  | 3250 | 0.3730          | 0.9286   |
| 0.0           | 14.0  | 3500 | 0.3750          | 0.9286   |
| 0.0           | 15.0  | 3750 | 0.3756          | 0.9286   |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0