metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- food101
metrics:
- precision
- recall
- f1
- 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[:5000]
args: default
metrics:
- name: Precision
type: precision
value: 0.8855567868882221
- name: Recall
type: recall
value: 0.887
- name: F1
type: f1
value: 0.8818977914615195
- name: Accuracy
type: accuracy
value: 0.887
my_awesome_food_model
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the food101 dataset. It achieves the following results on the evaluation set:
- Loss: 1.6405
- Precision: 0.8856
- Recall: 0.887
- F1: 0.8819
- Accuracy: 0.887
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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 2.7494 | 0.99 | 62 | 2.5554 | 0.7488 | 0.829 | 0.7859 | 0.829 |
| 1.9011 | 2.0 | 125 | 1.8058 | 0.8825 | 0.878 | 0.8645 | 0.878 |
| 1.6532 | 2.98 | 186 | 1.6405 | 0.8856 | 0.887 | 0.8819 | 0.887 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.13.3