metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-RU3-10
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7833333333333333
vit-base-patch16-224-RU3-10
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6241
- Accuracy: 0.7833
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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 1.3698 | 0.99 | 19 | 1.1845 | 0.65 |
| 1.1232 | 1.97 | 38 | 0.9393 | 0.65 |
| 0.8168 | 2.96 | 57 | 0.9117 | 0.6333 |
| 0.5992 | 4.0 | 77 | 0.8330 | 0.7333 |
| 0.4258 | 4.99 | 96 | 0.7471 | 0.7 |
| 0.3283 | 5.97 | 115 | 0.6241 | 0.7833 |
| 0.2543 | 6.96 | 134 | 0.5916 | 0.7833 |
| 0.2345 | 8.0 | 154 | 0.6783 | 0.7833 |
| 0.2027 | 8.99 | 173 | 0.6577 | 0.7833 |
| 0.1733 | 9.87 | 190 | 0.6589 | 0.7833 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0