metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: car_orientation_classification2
results: []
car_orientation_classification2
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2530
- Accuracy: 0.4806
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0298 | 1.0 | 17 | 1.8008 | 0.3428 |
| 1.6758 | 2.0 | 34 | 1.5297 | 0.4276 |
| 1.4213 | 3.0 | 51 | 1.3307 | 0.4523 |
| 1.3225 | 4.0 | 68 | 1.2899 | 0.4806 |
| 1.2432 | 5.0 | 85 | 1.2530 | 0.4806 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1