metadata
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-base-patch16-224
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: 0.6984126984126984
vit-base-patch16-224
This model was trained from scratch on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.6463
- Accuracy: 0.6984
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.6893 | 1.0 | 35 | 0.7319 | 0.4127 |
| 0.702 | 2.0 | 70 | 0.6863 | 0.5238 |
| 0.6644 | 3.0 | 105 | 0.6796 | 0.5873 |
| 0.645 | 4.0 | 140 | 0.6722 | 0.5714 |
| 0.6455 | 5.0 | 175 | 0.6545 | 0.6508 |
| 0.6456 | 6.0 | 210 | 0.6536 | 0.6508 |
| 0.6745 | 7.0 | 245 | 0.6463 | 0.6984 |
| 0.6369 | 8.0 | 280 | 0.6525 | 0.6667 |
| 0.6012 | 9.0 | 315 | 0.6486 | 0.6984 |
| 0.6219 | 10.0 | 350 | 0.6466 | 0.6984 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.4.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1