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: 0.8187772925764192
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: 0.5289
- Accuracy: 0.8188
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5055 | 1.16 | 150 | 0.5578 | 0.6943 |
| 0.4352 | 2.33 | 300 | 0.4578 | 0.7817 |
| 0.4009 | 3.49 | 450 | 0.4632 | 0.7795 |
| 0.295 | 4.65 | 600 | 0.5191 | 0.7729 |
| 0.297 | 5.81 | 750 | 0.4560 | 0.7926 |
| 0.2507 | 6.98 | 900 | 0.4803 | 0.7969 |
| 0.2317 | 8.14 | 1050 | 0.4836 | 0.7969 |
| 0.1745 | 9.3 | 1200 | 0.5272 | 0.7860 |
| 0.1714 | 10.47 | 1350 | 0.5344 | 0.8035 |
| 0.1437 | 11.63 | 1500 | 0.5477 | 0.7969 |
| 0.1356 | 12.79 | 1650 | 0.5300 | 0.7904 |
| 0.1148 | 13.95 | 1800 | 0.5289 | 0.8188 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0