metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-large-patch32-384
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: image_classification
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: 0.3
image_classification
This model is a fine-tuned version of google/vit-large-patch32-384 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.8452
- Accuracy: 0.3
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.1828 | 1.0 | 20 | 2.1899 | 0.1125 |
| 2.1419 | 2.0 | 40 | 2.1018 | 0.1625 |
| 2.078 | 3.0 | 60 | 2.1286 | 0.1625 |
| 2.0943 | 4.0 | 80 | 2.1462 | 0.15 |
| 2.0486 | 5.0 | 100 | 2.0665 | 0.2 |
| 1.9442 | 6.0 | 120 | 1.9868 | 0.2562 |
| 1.9307 | 7.0 | 140 | 1.9403 | 0.2375 |
| 1.8743 | 8.0 | 160 | 1.8866 | 0.275 |
| 1.7348 | 9.0 | 180 | 1.7927 | 0.3312 |
| 1.6455 | 10.0 | 200 | 1.7579 | 0.3187 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0