|
--- |
|
license: apache-2.0 |
|
base_model: nurizz/finetuned-indian-food |
|
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 [nurizz/finetuned-indian-food](https://huggingface.co/nurizz/finetuned-indian-food) on the indian_food_images dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2206 |
|
- Accuracy: 0.9458 |
|
|
|
## 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 | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 1.1092 | 0.3003 | 100 | 1.0007 | 0.8225 | |
|
| 0.7677 | 0.6006 | 200 | 0.6427 | 0.8533 | |
|
| 0.7808 | 0.9009 | 300 | 0.5790 | 0.8533 | |
|
| 0.3628 | 1.2012 | 400 | 0.5051 | 0.8629 | |
|
| 0.2928 | 1.5015 | 500 | 0.3815 | 0.9086 | |
|
| 0.3293 | 1.8018 | 600 | 0.3522 | 0.9065 | |
|
| 0.2239 | 2.1021 | 700 | 0.3320 | 0.9086 | |
|
| 0.288 | 2.4024 | 800 | 0.3520 | 0.9065 | |
|
| 0.3209 | 2.7027 | 900 | 0.2842 | 0.9299 | |
|
| 0.187 | 3.0030 | 1000 | 0.2577 | 0.9352 | |
|
| 0.1801 | 3.3033 | 1100 | 0.2511 | 0.9341 | |
|
| 0.2028 | 3.6036 | 1200 | 0.2210 | 0.9469 | |
|
| 0.1564 | 3.9039 | 1300 | 0.2206 | 0.9458 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
