metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: colab20240326ryan
results: []
colab20240326ryan
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: 0.8730
- Accuracy: 0.6652
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 |
|---|---|---|---|---|
| 0.7644 | 0.05 | 100 | 0.8799 | 0.6399 |
| 0.6947 | 0.09 | 200 | 0.9719 | 0.6044 |
| 0.6656 | 0.14 | 300 | 0.8993 | 0.6590 |
| 0.6741 | 0.19 | 400 | 0.9202 | 0.6351 |
| 0.5095 | 0.23 | 500 | 0.8826 | 0.6557 |
| 0.602 | 0.28 | 600 | 0.8469 | 0.6617 |
| 0.5516 | 0.32 | 700 | 0.9219 | 0.6567 |
| 0.6998 | 0.37 | 800 | 0.9070 | 0.6409 |
| 0.5686 | 0.42 | 900 | 0.8590 | 0.6572 |
| 0.6308 | 0.46 | 1000 | 0.9953 | 0.6165 |
| 0.6242 | 0.51 | 1100 | 0.8730 | 0.6652 |
Framework versions
- Transformers 4.39.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2