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: 0.8209606986899564
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: 0.4822
- Accuracy: 0.8210
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4892 | 1.16 | 150 | 0.5660 | 0.7271 |
| 0.4346 | 2.33 | 300 | 0.4475 | 0.7860 |
| 0.4072 | 3.49 | 450 | 0.4499 | 0.7882 |
| 0.312 | 4.65 | 600 | 0.5289 | 0.7598 |
| 0.2913 | 5.81 | 750 | 0.4868 | 0.8100 |
| 0.2389 | 6.98 | 900 | 0.4596 | 0.8079 |
| 0.2176 | 8.14 | 1050 | 0.4642 | 0.8210 |
| 0.183 | 9.3 | 1200 | 0.4822 | 0.8210 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0