|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: finetuned-indian-food |
|
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. --> |
|
|
|
# finetuned-indian-food |
|
|
|
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 indian_food_images dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2867 |
|
- Accuracy: 0.9267 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 4 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 1.0192 | 0.3003 | 100 | 0.9248 | 0.8480 | |
|
| 0.635 | 0.6006 | 200 | 0.5917 | 0.8863 | |
|
| 0.6523 | 0.9009 | 300 | 0.5134 | 0.8799 | |
|
| 0.4247 | 1.2012 | 400 | 0.3983 | 0.9044 | |
|
| 0.4393 | 1.5015 | 500 | 0.4119 | 0.8980 | |
|
| 0.4631 | 1.8018 | 600 | 0.3752 | 0.9107 | |
|
| 0.2992 | 2.1021 | 700 | 0.3469 | 0.9129 | |
|
| 0.3 | 2.4024 | 800 | 0.3157 | 0.9203 | |
|
| 0.2372 | 2.7027 | 900 | 0.3210 | 0.9192 | |
|
| 0.2447 | 3.0030 | 1000 | 0.3140 | 0.9224 | |
|
| 0.2209 | 3.3033 | 1100 | 0.3034 | 0.9160 | |
|
| 0.2641 | 3.6036 | 1200 | 0.2896 | 0.9277 | |
|
| 0.0954 | 3.9039 | 1300 | 0.2867 | 0.9267 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
