metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: dvm-cars-vit-first-5k
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: TalonMeyer/dvm-cars-dataset-first-5k
type: imagefolder
config: default
split: validation
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.4431137724550898
dvm-cars-vit-first-5k
This model is a fine-tuned version of google/vit-base-patch16-224 on the TalonMeyer/dvm-cars-dataset-first-5k dataset. It achieves the following results on the evaluation set:
- Loss: 2.3711
- Accuracy: 0.4431
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: 0.0003
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.1701 | 1.0 | 251 | 2.9441 | 0.2994 |
| 2.5577 | 2.0 | 502 | 2.6693 | 0.3333 |
| 2.3469 | 3.0 | 753 | 2.5099 | 0.3593 |
| 2.1792 | 4.0 | 1004 | 2.4285 | 0.4032 |
| 2.0967 | 5.0 | 1255 | 2.4063 | 0.4152 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1