convnext-tiny-224-finetuned-noh
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: 0.3730
- Accuracy: 0.8801
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5518 | 1.0 | 23 | 0.5414 | 0.7619 |
| 0.5027 | 2.0 | 46 | 0.4834 | 0.7619 |
| 0.4616 | 3.0 | 69 | 0.4075 | 0.8358 |
| 0.4001 | 4.0 | 92 | 0.3601 | 0.8571 |
| 0.3698 | 5.0 | 115 | 0.3467 | 0.8768 |
| 0.3261 | 6.0 | 138 | 0.3730 | 0.8801 |
| 0.301 | 7.0 | 161 | 0.3728 | 0.8736 |
| 0.3071 | 8.0 | 184 | 0.3959 | 0.8374 |
| 0.264 | 9.0 | 207 | 0.3865 | 0.8604 |
| 0.2769 | 9.5778 | 220 | 0.3873 | 0.8621 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.21.0