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: 0.5189
- Accuracy: 0.8045
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: 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 |
|---|---|---|---|---|
| 1.1031 | 1.0 | 130 | 1.0313 | 0.5038 |
| 1.0087 | 2.0 | 260 | 0.9253 | 0.5789 |
| 0.8781 | 3.0 | 390 | 0.8823 | 0.6617 |
| 0.7127 | 4.0 | 520 | 0.6853 | 0.7068 |
| 0.6784 | 5.0 | 650 | 0.7131 | 0.7143 |
| 0.6864 | 6.0 | 780 | 0.7314 | 0.6992 |
| 0.5986 | 7.0 | 910 | 0.6224 | 0.7218 |
| 0.5956 | 8.0 | 1040 | 0.5261 | 0.7744 |
| 0.6009 | 9.0 | 1170 | 0.5274 | 0.8120 |
| 0.5433 | 10.0 | 1300 | 0.5189 | 0.8045 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1