metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-images
results: []
vit-base-images
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: 0.3465
- Accuracy: 0.905
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: 0.0002
- 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7334 | 0.4 | 100 | 0.6142 | 0.779 |
| 0.6032 | 0.8 | 200 | 0.5516 | 0.808 |
| 0.4725 | 1.2 | 300 | 0.4390 | 0.854 |
| 0.3638 | 1.6 | 400 | 0.4622 | 0.822 |
| 0.3279 | 2.0 | 500 | 0.3772 | 0.876 |
| 0.1337 | 2.4 | 600 | 0.4518 | 0.869 |
| 0.236 | 2.8 | 700 | 0.3766 | 0.878 |
| 0.0275 | 3.2 | 800 | 0.3518 | 0.891 |
| 0.0427 | 3.6 | 900 | 0.3709 | 0.896 |
| 0.0363 | 4.0 | 1000 | 0.3465 | 0.905 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1