metadata
license: apache-2.0
base_model: jessicagabriel/my_awesome_food_model
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- accuracy
model-index:
- name: my_awesome_food_model
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: food101
type: food101
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.8900990099009901
my_awesome_food_model
This model is a fine-tuned version of jessicagabriel/my_awesome_food_model on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4388
- Accuracy: 0.8901
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 |
|---|---|---|---|---|
| 0.4631 | 1.0 | 947 | 0.4695 | 0.8811 |
| 0.4759 | 2.0 | 1894 | 0.5028 | 0.8700 |
| 0.3744 | 3.0 | 2841 | 0.4840 | 0.8754 |
| 0.3198 | 4.0 | 3788 | 0.4823 | 0.8769 |
| 0.3655 | 5.0 | 4735 | 0.4658 | 0.8815 |
| 0.2994 | 6.0 | 5682 | 0.4854 | 0.8770 |
| 0.2268 | 7.0 | 6629 | 0.4617 | 0.8837 |
| 0.2735 | 8.0 | 7576 | 0.4479 | 0.8874 |
| 0.1579 | 9.0 | 8523 | 0.4487 | 0.8874 |
| 0.2327 | 10.0 | 9470 | 0.4388 | 0.8901 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3