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-RX2-12
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: 0.7391304347826086
vit-base-patch16-224-RX2-12
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: 0.7887
- Accuracy: 0.7391
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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3604 | 0.94 | 11 | 1.2834 | 0.4783 |
| 1.2312 | 1.96 | 23 | 1.1356 | 0.6522 |
| 1.0933 | 2.98 | 35 | 1.0386 | 0.6739 |
| 0.936 | 4.0 | 47 | 0.9049 | 0.6739 |
| 0.8011 | 4.94 | 58 | 0.9847 | 0.6087 |
| 0.616 | 5.96 | 70 | 0.9236 | 0.6304 |
| 0.5251 | 6.98 | 82 | 0.8640 | 0.6522 |
| 0.4618 | 8.0 | 94 | 0.8612 | 0.7174 |
| 0.3974 | 8.94 | 105 | 0.8461 | 0.6522 |
| 0.3532 | 9.96 | 117 | 0.7887 | 0.7391 |
| 0.335 | 10.98 | 129 | 0.7995 | 0.7174 |
| 0.3211 | 11.23 | 132 | 0.8058 | 0.7174 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0