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-ve-U10-12
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: 0.7843137254901961
vit-base-patch16-224-ve-U10-12
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: 0.6632
- Accuracy: 0.7843
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 |
---|---|---|---|---|
1.3629 | 0.95 | 15 | 1.2289 | 0.4706 |
1.1038 | 1.97 | 31 | 1.0413 | 0.5882 |
0.9375 | 2.98 | 47 | 0.8989 | 0.5882 |
0.6917 | 4.0 | 63 | 0.8520 | 0.7059 |
0.5862 | 4.95 | 78 | 0.6827 | 0.7255 |
0.4042 | 5.97 | 94 | 0.7281 | 0.7255 |
0.2987 | 6.98 | 110 | 0.7262 | 0.7647 |
0.2571 | 8.0 | 126 | 0.7604 | 0.7255 |
0.2326 | 8.95 | 141 | 0.6632 | 0.7843 |
0.1994 | 9.97 | 157 | 0.6744 | 0.7451 |
0.1968 | 10.98 | 173 | 0.6864 | 0.7451 |
0.1847 | 11.43 | 180 | 0.6647 | 0.7451 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0