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-pure-ViT
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: 0.8714733542319749
vit-base-patch16-224-pure-ViT
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: 0.3270
- Accuracy: 0.8715
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: 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: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4676 | 1.0 | 202 | 0.4042 | 0.8095 |
| 0.4605 | 2.0 | 404 | 0.3675 | 0.8377 |
| 0.4012 | 3.0 | 606 | 0.3486 | 0.8506 |
| 0.3727 | 4.0 | 808 | 0.3413 | 0.8481 |
| 0.3482 | 5.0 | 1010 | 0.3339 | 0.8614 |
| 0.354 | 6.0 | 1212 | 0.3436 | 0.8561 |
| 0.3212 | 7.0 | 1414 | 0.3415 | 0.8534 |
| 0.3263 | 8.0 | 1616 | 0.3281 | 0.8642 |
| 0.285 | 9.0 | 1818 | 0.3263 | 0.8673 |
| 0.2779 | 10.0 | 2020 | 0.3270 | 0.8715 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2