metadata
base_model: google/vit-base-patch16-224-in21k
library_name: peft
license: apache-2.0
metrics:
- accuracy
tags:
- generated_from_trainer
model-index:
- name: vit-base-patch16-224-in21k-finetuned-lora-food101
results: []
vit-base-patch16-224-in21k-finetuned-lora-food101
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: 0.2481
- Accuracy: 0.9279
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: 168
- eval_batch_size: 168
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 672
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.8568 | 0.9933 | 74 | 0.3500 | 0.8978 |
| 0.7674 | 2.0 | 149 | 0.3065 | 0.9089 |
| 0.724 | 2.9933 | 223 | 0.2805 | 0.9164 |
| 0.6316 | 4.0 | 298 | 0.2725 | 0.9197 |
| 0.6462 | 4.9933 | 372 | 0.2659 | 0.9195 |
| 0.5809 | 6.0 | 447 | 0.2623 | 0.9223 |
| 0.5212 | 6.9933 | 521 | 0.2624 | 0.9217 |
| 0.5561 | 8.0 | 596 | 0.2523 | 0.9259 |
| 0.5061 | 8.9933 | 670 | 0.2502 | 0.9268 |
| 0.4955 | 9.9329 | 740 | 0.2481 | 0.9279 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0