metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- image_folder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224-in21k-finetuned
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: image_folder
type: image_folder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.7057676232933965
vit-base-patch16-224-in21k-finetuned
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.9803
- Accuracy: 0.7058
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 |
|---|---|---|---|---|
| 0.4887 | 1.0 | 224 | 0.9213 | 0.6776 |
| 0.4969 | 2.0 | 449 | 0.9038 | 0.6927 |
| 0.4095 | 3.0 | 673 | 0.9077 | 0.6977 |
| 0.3344 | 4.0 | 898 | 0.9398 | 0.6989 |
| 0.3055 | 5.0 | 1122 | 0.9803 | 0.7058 |
| 0.2214 | 6.0 | 1347 | 1.0337 | 0.6953 |
| 0.1575 | 7.0 | 1571 | 1.0642 | 0.6977 |
| 0.1169 | 8.0 | 1796 | 1.0829 | 0.7030 |
| 0.0917 | 9.0 | 2020 | 1.1121 | 0.7048 |
| 0.0785 | 9.98 | 2240 | 1.1280 | 0.7052 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.15.0