dark-pond-236
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: 0.1304
- Accuracy: 0.9611
- Precision: 0.9611
- Recall: 0.9611
- F1: 0.9611
- Roc Auc: 0.9990
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: 0.0001
- train_batch_size: 256
- eval_batch_size: 256
- 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Roc Auc |
|---|---|---|---|---|---|---|---|---|
| 1.4605 | 1.0 | 161 | 0.4303 | 0.8863 | 0.8910 | 0.8863 | 0.8860 | 0.9934 |
| 0.6333 | 2.0 | 322 | 0.2051 | 0.9418 | 0.9423 | 0.9418 | 0.9418 | 0.9980 |
| 0.5099 | 3.0 | 483 | 0.1538 | 0.9539 | 0.9540 | 0.9539 | 0.9538 | 0.9987 |
| 0.4501 | 4.0 | 644 | 0.1353 | 0.9606 | 0.9605 | 0.9606 | 0.9605 | 0.9989 |
| 0.4281 | 5.0 | 805 | 0.1304 | 0.9611 | 0.9611 | 0.9611 | 0.9611 | 0.9990 |
Framework versions
- Transformers 4.52.3
- Pytorch 2.7.0+cpu
- Datasets 3.6.0
- Tokenizers 0.21.0