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: 0.7939814814814815
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: 0.5004
- Accuracy: 0.7940
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: 4e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 69
- 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 |
|---|---|---|---|---|
| 0.5938 | 0.62 | 150 | 0.5738 | 0.7199 |
| 0.4934 | 1.23 | 300 | 0.5229 | 0.7454 |
| 0.5048 | 1.85 | 450 | 0.5361 | 0.7222 |
| 0.4615 | 2.47 | 600 | 0.4958 | 0.7685 |
| 0.4591 | 3.09 | 750 | 0.4720 | 0.7639 |
| 0.3679 | 3.7 | 900 | 0.5321 | 0.7454 |
| 0.3366 | 4.32 | 1050 | 0.6765 | 0.7083 |
| 0.3057 | 4.94 | 1200 | 0.4633 | 0.7940 |
| 0.316 | 5.56 | 1350 | 0.5217 | 0.7639 |
| 0.3186 | 6.17 | 1500 | 0.5226 | 0.7708 |
| 0.2319 | 6.79 | 1650 | 0.5004 | 0.7940 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.0.1+cu117
- Datasets 2.15.0
- Tokenizers 0.15.0