metadata
library_name: peft
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- base_model:adapter:google/vit-base-patch16-224-in21k
- lora
- transformers
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: vit-finetuned-chessman2
results:
- task:
type: image-classification
name: Image Classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- type: accuracy
value: 0.9636363636363636
name: Accuracy
vit-finetuned-chessman2
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1620
- Accuracy: 0.9636
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5954 | 1.0 | 28 | 1.3698 | 0.6545 |
| 0.9802 | 2.0 | 56 | 0.7982 | 0.8 |
| 0.4706 | 3.0 | 84 | 0.4171 | 0.9455 |
| 0.2342 | 4.0 | 112 | 0.2657 | 0.9455 |
| 0.1416 | 5.0 | 140 | 0.2017 | 0.9636 |
| 0.1059 | 6.0 | 168 | 0.1813 | 0.9636 |
| 0.0872 | 7.0 | 196 | 0.1655 | 0.9636 |
| 0.0749 | 8.0 | 224 | 0.1620 | 0.9636 |
Framework versions
- PEFT 0.19.1
- Transformers 4.57.6
- Pytorch 2.10.0
- Datasets 5.0.0
- Tokenizers 0.22.2