metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: my_awesome_food_model
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: 0.9795191451469278
my_awesome_food_model
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: 1.1312
- Accuracy: 0.9795
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.9594 | 1.0 | 70 | 3.8779 | 0.6189 |
| 3.0869 | 1.99 | 140 | 3.0415 | 0.8549 |
| 2.471 | 2.99 | 210 | 2.4433 | 0.9270 |
| 2.0406 | 4.0 | 281 | 2.0261 | 0.9501 |
| 1.7238 | 5.0 | 351 | 1.7346 | 0.9581 |
| 1.4513 | 5.99 | 421 | 1.4902 | 0.9671 |
| 1.3131 | 6.99 | 491 | 1.3221 | 0.9786 |
| 1.1752 | 8.0 | 562 | 1.2230 | 0.9768 |
| 1.1007 | 9.0 | 632 | 1.1619 | 0.9795 |
| 1.0682 | 9.96 | 700 | 1.1312 | 0.9795 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3