convnextv2-tiny-1k-224-finetuned-cifar10
This model is a fine-tuned version of facebook/convnextv2-tiny-1k-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6668
- Accuracy: 0.8427
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: 256
- eval_batch_size: 256
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 1024
- 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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.516 | 1.0 | 41 | 1.2639 | 0.6939 |
| 1.0647 | 2.0 | 82 | 0.7782 | 0.8099 |
| 0.9449 | 2.9441 | 120 | 0.6668 | 0.8427 |
Framework versions
- Transformers 4.49.0
- Pytorch 2.7.0+cpu
- Datasets 3.3.2
- Tokenizers 0.21.0