metadata
base_model: nateraw/vit-age-classifier
tags:
- generated_from_trainer
datasets:
- fair_face
metrics:
- accuracy
model-index:
- name: image_age_classification
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: fair_face
type: fair_face
config: '0.25'
split: train[:10000]
args: '0.25'
metrics:
- name: Accuracy
type: accuracy
value: 0.601
image_age_classification
This model is a fine-tuned version of nateraw/vit-age-classifier on the fair_face dataset. It achieves the following results on the evaluation set:
- Loss: 0.9464
- Accuracy: 0.601
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.9107 | 1.0 | 125 | 0.9360 | 0.6065 |
| 0.7945 | 2.0 | 250 | 0.9545 | 0.588 |
| 1.0256 | 3.0 | 375 | 1.0144 | 0.586 |
| 0.7354 | 4.0 | 500 | 0.9726 | 0.594 |
| 0.6979 | 5.0 | 625 | 0.9735 | 0.5995 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 1.12.1+cu116
- Datasets 2.14.5
- Tokenizers 0.12.1