metadata
library_name: transformers
license: apache-2.0
base_model: WinKawaks/vit-tiny-patch16-224
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: gender_mozilla_mel_spec_Vit_vit-tiny-patch16-224_2
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: default
split: train
args: default
metrics:
- name: Accuracy
type: accuracy
value: 0.9366666666666666
gender_mozilla_mel_spec_Vit_vit-tiny-patch16-224_2
This model is a fine-tuned version of WinKawaks/vit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3420
- Accuracy: 0.9367
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6724 | 1.0 | 11 | 0.3985 | 0.87 |
| 0.3071 | 2.0 | 22 | 0.2514 | 0.92 |
| 0.1861 | 3.0 | 33 | 0.2074 | 0.93 |
| 0.1192 | 4.0 | 44 | 0.2194 | 0.94 |
| 0.0655 | 5.0 | 55 | 0.2362 | 0.9367 |
| 0.0268 | 6.0 | 66 | 0.2645 | 0.9333 |
| 0.0239 | 7.0 | 77 | 0.3006 | 0.9333 |
| 0.0049 | 8.0 | 88 | 0.3445 | 0.9333 |
| 0.007 | 9.0 | 99 | 0.3609 | 0.93 |
| 0.0005 | 10.0 | 110 | 0.3420 | 0.9367 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0