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-RU5-10
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: 0.5833333333333334
vit-base-patch16-224-RU5-10
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: 1.2348
- Accuracy: 0.5833
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 2 | 1.3715 | 0.4833 |
| No log | 2.0 | 4 | 1.3415 | 0.4667 |
| No log | 3.0 | 6 | 1.3148 | 0.4667 |
| No log | 4.0 | 8 | 1.2919 | 0.4833 |
| 1.3369 | 5.0 | 10 | 1.2726 | 0.4833 |
| 1.3369 | 6.0 | 12 | 1.2569 | 0.5 |
| 1.3369 | 7.0 | 14 | 1.2442 | 0.55 |
| 1.3369 | 8.0 | 16 | 1.2348 | 0.5833 |
| 1.3369 | 9.0 | 18 | 1.2287 | 0.5833 |
| 1.2441 | 10.0 | 20 | 1.2261 | 0.5667 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0