metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: genderage_convnext
results: []
genderage_convnext
This model is a fine-tuned version of facebook/convnext-base-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.3896
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: 1e-05
- train_batch_size: 11
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5114 | 0.89 | 100 | 0.4998 |
| 0.425 | 1.79 | 200 | 0.4246 |
| 0.4124 | 2.68 | 300 | 0.4100 |
| 0.4034 | 3.57 | 400 | 0.4037 |
| 0.3938 | 4.46 | 500 | 0.3992 |
| 0.4021 | 5.36 | 600 | 0.3952 |
| 0.3843 | 6.25 | 700 | 0.3918 |
| 0.3804 | 7.14 | 800 | 0.3896 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2