metadata
library_name: transformers
license: apache-2.0
base_model: facebook/convnext-tiny-224
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: convnext-gender-classifier
results: []
convnext-gender-classifier
This model is a fine-tuned version of facebook/convnext-tiny-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1894
- Accuracy: 0.956
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
- optimizer: Use OptimizerNames.ADAMW_TORCH 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 |
|---|---|---|---|---|
| 0.0205 | 1.0 | 157 | 0.1179 | 0.969 |
| 0.0215 | 2.0 | 314 | 0.1396 | 0.969 |
| 0.0017 | 3.0 | 471 | 0.1386 | 0.967 |
| 0.0207 | 4.0 | 628 | 0.1490 | 0.968 |
| 0.0111 | 5.0 | 785 | 0.1563 | 0.966 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0