metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- vision-transformer
- flowers
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: flower-vit
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: custom flower dataset
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9636363636363636
- name: Precision
type: precision
value: 0.9632702640149449
- name: Recall
type: recall
value: 0.9636363636363636
- name: F1
type: f1
value: 0.9632142875960066
flower-vit
This model is a fine-tuned version of google/vit-base-patch16-224 on the custom flower dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1623
- Accuracy: 0.9636
- Precision: 0.9633
- Recall: 0.9636
- F1: 0.9632
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: 0.0003
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.1765 | 1.0 | 138 | 0.1646 | 0.9673 | 0.9679 | 0.9673 | 0.9673 |
| 0.1386 | 2.0 | 276 | 0.1291 | 0.9673 | 0.9681 | 0.9673 | 0.9673 |
| 0.0889 | 3.0 | 414 | 0.1214 | 0.9673 | 0.9681 | 0.9673 | 0.9673 |
| 0.0857 | 4.0 | 552 | 0.1183 | 0.9673 | 0.9681 | 0.9673 | 0.9673 |
| 0.0942 | 5.0 | 690 | 0.1177 | 0.9673 | 0.9681 | 0.9673 | 0.9673 |
Framework versions
- Transformers 5.5.4
- Pytorch 2.11.0+cpu
- Datasets 4.8.4
- Tokenizers 0.22.2