metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: attraction-classifier
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: 0.8242677824267782
attraction-classifier
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: 0.4274
- Accuracy: 0.8243
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: 32
- eval_batch_size: 32
- seed: 69
- gradient_accumulation_steps: 16
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 25
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6782 | 1.78 | 15 | 0.5922 | 0.7008 |
| 0.5096 | 3.56 | 30 | 0.5153 | 0.7552 |
| 0.4434 | 5.33 | 45 | 0.4520 | 0.7762 |
| 0.3844 | 7.11 | 60 | 0.4381 | 0.8013 |
| 0.3642 | 8.89 | 75 | 0.4359 | 0.8054 |
| 0.322 | 10.67 | 90 | 0.4086 | 0.8138 |
| 0.2845 | 12.44 | 105 | 0.4111 | 0.8201 |
| 0.2588 | 14.22 | 120 | 0.4100 | 0.8159 |
| 0.2516 | 16.0 | 135 | 0.4122 | 0.8389 |
| 0.2375 | 17.78 | 150 | 0.4085 | 0.8243 |
| 0.2309 | 19.56 | 165 | 0.4149 | 0.8117 |
| 0.2175 | 21.33 | 180 | 0.4274 | 0.8243 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0