metadata
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- image-classification
- vision
- generated_from_trainer
model-index:
- name: only-lora-beans-vit-base-patch16-224-in21k
results: []
only-lora-beans-vit-base-patch16-224-in21k
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the beans dataset. It achieves the following results on the evaluation set:
- Loss: 0.0752
- Accuracy: 0.9624
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: 0.005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4846 | 1.0 | 130 | 0.0752 | 0.9624 |
| 0.3473 | 2.0 | 260 | 0.1599 | 0.9549 |
| 0.2953 | 3.0 | 390 | 0.1192 | 0.9549 |
| 0.2653 | 4.0 | 520 | 0.1393 | 0.9398 |
| 0.2344 | 5.0 | 650 | 0.1001 | 0.9624 |
| 0.21 | 6.0 | 780 | 0.0893 | 0.9624 |
| 0.3117 | 7.0 | 910 | 0.1933 | 0.9248 |
| 0.2459 | 8.0 | 1040 | 0.1901 | 0.9248 |
| 0.25 | 9.0 | 1170 | 0.0868 | 0.9699 |
| 0.2038 | 10.0 | 1300 | 0.1528 | 0.9474 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1