metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: Tb_Dataset
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: 0.875
Tb_Dataset
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4037
- Accuracy: 0.875
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0996 | 0.3067 | 100 | 1.0429 | 0.5625 |
| 0.0481 | 0.6135 | 200 | 0.5665 | 0.8125 |
| 0.0391 | 0.9202 | 300 | 1.0037 | 0.6875 |
| 0.0711 | 1.2270 | 400 | 0.5200 | 0.875 |
| 0.0258 | 1.5337 | 500 | 0.3818 | 0.9375 |
| 0.0547 | 1.8405 | 600 | 0.3415 | 0.9375 |
| 0.0029 | 2.1472 | 700 | 0.0637 | 0.9375 |
| 0.0543 | 2.4540 | 800 | 0.7362 | 0.8125 |
| 0.0265 | 2.7607 | 900 | 1.0917 | 0.75 |
| 0.0017 | 3.0675 | 1000 | 0.0030 | 1.0 |
| 0.0054 | 3.3742 | 1100 | 0.0364 | 1.0 |
| 0.0234 | 3.6810 | 1200 | 0.2310 | 0.875 |
| 0.0076 | 3.9877 | 1300 | 0.4037 | 0.875 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1