---
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: vit-base-patch16-224-in21k-lora
  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. -->

[<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/sajjadi/Fast-PEFT/runs/wwmmlus9)
[<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/sajjadi/Fast-PEFT/runs/wwmmlus9)
# vit-base-patch16-224-in21k-lora

This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.1792
- Accuracy: 0.51

## 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: 0.002
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 1    | 4.5231          | 0.11     |
| No log        | 2.0   | 2    | 4.4533          | 0.22     |
| No log        | 3.0   | 3    | 4.3921          | 0.35     |
| No log        | 4.0   | 4    | 4.3390          | 0.41     |
| 4.4319        | 5.0   | 5    | 4.2933          | 0.46     |
| 4.4319        | 6.0   | 6    | 4.2553          | 0.48     |
| 4.4319        | 7.0   | 7    | 4.2247          | 0.51     |
| 4.4319        | 8.0   | 8    | 4.2020          | 0.51     |
| 4.4319        | 9.0   | 9    | 4.1866          | 0.51     |
| 4.1334        | 10.0  | 10   | 4.1792          | 0.51     |


### Framework versions

- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0