|
--- |
|
license: apache-2.0 |
|
base_model: google/vit-base-patch16-224-in21k |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
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 an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2293 |
|
- Accuracy: 0.9405 |
|
- Precision: 0.9395 |
|
- Recall: 0.9420 |
|
- F1: 0.9402 |
|
|
|
## 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 | Precision | Recall | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:| |
|
| 0.8589 | 0.3 | 100 | 0.5618 | 0.8714 | 0.8981 | 0.8620 | 0.8696 | |
|
| 0.6973 | 0.6 | 200 | 0.5544 | 0.8608 | 0.8742 | 0.8690 | 0.8630 | |
|
| 0.4078 | 0.9 | 300 | 0.4671 | 0.8831 | 0.8915 | 0.8840 | 0.8812 | |
|
| 0.3818 | 1.2 | 400 | 0.4203 | 0.8884 | 0.9017 | 0.8864 | 0.8877 | |
|
| 0.2262 | 1.5 | 500 | 0.3481 | 0.9107 | 0.9177 | 0.9085 | 0.9098 | |
|
| 0.2137 | 1.8 | 600 | 0.3761 | 0.9022 | 0.9094 | 0.9027 | 0.9026 | |
|
| 0.4515 | 2.1 | 700 | 0.3722 | 0.9044 | 0.9091 | 0.9041 | 0.9017 | |
|
| 0.3024 | 2.4 | 800 | 0.3105 | 0.9203 | 0.9198 | 0.9220 | 0.9188 | |
|
| 0.1748 | 2.7 | 900 | 0.2767 | 0.9288 | 0.9274 | 0.9293 | 0.9272 | |
|
| 0.1959 | 3.0 | 1000 | 0.2825 | 0.9256 | 0.9318 | 0.9243 | 0.9230 | |
|
| 0.1663 | 3.3 | 1100 | 0.2549 | 0.9341 | 0.9362 | 0.9366 | 0.9356 | |
|
| 0.0513 | 3.6 | 1200 | 0.2254 | 0.9416 | 0.9436 | 0.9422 | 0.9424 | |
|
| 0.1478 | 3.9 | 1300 | 0.2293 | 0.9405 | 0.9395 | 0.9420 | 0.9402 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|