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-lora
results: []
vit-base-patch16-224-in21k-lora
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: 4.1775
- Accuracy: 0.53
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: 0.002
- train_batch_size: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 1 | 4.5232 | 0.07 |
| No log | 2.0 | 2 | 4.4532 | 0.18 |
| No log | 3.0 | 3 | 4.3919 | 0.35 |
| No log | 4.0 | 4 | 4.3384 | 0.42 |
| 4.4214 | 5.0 | 5 | 4.2923 | 0.44 |
| 4.4214 | 6.0 | 6 | 4.2543 | 0.48 |
| 4.4214 | 7.0 | 7 | 4.2232 | 0.49 |
| 4.4214 | 8.0 | 8 | 4.2006 | 0.52 |
| 4.4214 | 9.0 | 9 | 4.1852 | 0.53 |
| 4.1244 | 10.0 | 10 | 4.1775 | 0.53 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0