metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: finetuned-indian-food
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9543039319872476
finetuned-indian-food
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1918
- Accuracy: 0.9543
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 |
---|---|---|---|---|
1.0175 | 0.3 | 100 | 0.9247 | 0.8629 |
0.7418 | 0.6 | 200 | 0.5536 | 0.8990 |
0.6652 | 0.9 | 300 | 0.4036 | 0.9182 |
0.5959 | 1.2 | 400 | 0.4022 | 0.8980 |
0.4478 | 1.5 | 500 | 0.3247 | 0.9288 |
0.4717 | 1.8 | 600 | 0.3019 | 0.9267 |
0.34 | 2.1 | 700 | 0.2594 | 0.9352 |
0.3518 | 2.4 | 800 | 0.2507 | 0.9352 |
0.3352 | 2.7 | 900 | 0.2484 | 0.9426 |
0.2493 | 3.0 | 1000 | 0.2266 | 0.9394 |
0.2034 | 3.3 | 1100 | 0.2011 | 0.9479 |
0.1753 | 3.6 | 1200 | 0.2089 | 0.9447 |
0.1614 | 3.9 | 1300 | 0.1918 | 0.9543 |
Framework versions
- Transformers 4.21.0
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1