nsfw-fine-tuned-timm-augmented
This model is a fine-tuned version of umairrkhn/nsfw-fine-tuned-timm on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0001
- Accuracy: 1.0
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1.5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0135 | 0.2533 | 500 | 0.0047 | 0.999 |
| 0.0188 | 0.5066 | 1000 | 0.0002 | 1.0 |
| 0.0123 | 0.7599 | 1500 | 0.0082 | 0.998 |
| 0.0111 | 1.0132 | 2000 | 0.0000 | 1.0 |
| 0.0031 | 1.2665 | 2500 | 0.0000 | 1.0 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.2
- Tokenizers 0.21.0