metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-large-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-large-patch16-224-dungeon-geo-morphs-0-4-26Nov24-001
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: 0.9938775510204082
vit-large-patch16-224-dungeon-geo-morphs-0-4-26Nov24-001
This model is a fine-tuned version of google/vit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0282
- Accuracy: 0.9939
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use 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_ratio: 0.1
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2849 | 4.4444 | 10 | 0.6545 | 0.8837 |
| 0.2089 | 8.8889 | 20 | 0.1889 | 0.9694 |
| 0.0278 | 13.3333 | 30 | 0.0619 | 0.9878 |
| 0.0034 | 17.7778 | 40 | 0.0349 | 0.9918 |
| 0.0012 | 22.2222 | 50 | 0.0282 | 0.9918 |
| 0.0008 | 26.6667 | 60 | 0.0282 | 0.9939 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3