metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: art_classifier
results: []
art_classifier
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6729
- Accuracy: 0.8868
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.8571 | 3 | 1.0830 | 0.3962 |
| No log | 2.0 | 7 | 1.0106 | 0.6415 |
| 1.0286 | 2.8571 | 10 | 0.9347 | 0.8302 |
| 1.0286 | 4.0 | 14 | 0.8509 | 0.8679 |
| 1.0286 | 4.8571 | 17 | 0.7853 | 0.8868 |
| 0.7956 | 6.0 | 21 | 0.7458 | 0.8868 |
| 0.7956 | 6.8571 | 24 | 0.7045 | 0.8679 |
| 0.7956 | 8.0 | 28 | 0.6863 | 0.8868 |
| 0.6554 | 8.5714 | 30 | 0.6729 | 0.8868 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1