convnext-large-384-22k-1k-Kontur-competition
This model is a fine-tuned version of facebook/convnext-large-384-22k-1k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0020
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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0003 | 1.0 | 717 | 0.0073 |
| 0.0035 | 2.0 | 1434 | 0.0050 |
| 0.0 | 3.0 | 2151 | 0.0020 |
| 0.0 | 4.0 | 2869 | 0.0000 |
| 0.0 | 5.0 | 3585 | 0.0020 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2