ConvNeXtV2_Tiny_v2
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: 0.0984
- Accuracy: 0.9642
- Precision: 0.9494
- Recall: 0.9744
- F1: 0.9617
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 77
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2391 | 1.0 | 111 | 0.2148 | 0.8799 | 0.8108 | 0.9652 | 0.8813 |
| 0.1959 | 2.0 | 222 | 0.1468 | 0.9422 | 0.9139 | 0.9658 | 0.9392 |
| 0.1968 | 3.0 | 333 | 0.1302 | 0.9479 | 0.9187 | 0.9731 | 0.9452 |
| 0.1787 | 4.0 | 444 | 0.1308 | 0.9417 | 0.9058 | 0.9750 | 0.9391 |
| 0.1747 | 5.0 | 555 | 0.1157 | 0.9507 | 0.9231 | 0.9744 | 0.9480 |
| 0.1402 | 6.0 | 666 | 0.1102 | 0.9521 | 0.9262 | 0.9737 | 0.9494 |
| 0.1511 | 7.0 | 777 | 0.0984 | 0.9642 | 0.9494 | 0.9744 | 0.9617 |
Framework versions
- Transformers 5.2.0
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.2