metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetuned-indian-food
results: []
finetuned-indian-food
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown 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