convnext-base-384-22k-1k-Kontur-competition-1.3K
This model is a fine-tuned version of facebook/convnext-base-384-22k-1k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0003
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.95 | 9 | 0.5273 |
| 0.6611 | 2.0 | 19 | 0.1518 |
| 0.2686 | 2.95 | 28 | 0.0266 |
| 0.0899 | 4.0 | 38 | 0.0066 |
| 0.0379 | 4.95 | 47 | 0.0025 |
| 0.0202 | 6.0 | 57 | 0.0020 |
| 0.0048 | 6.95 | 66 | 0.0010 |
| 0.0056 | 8.0 | 76 | 0.0011 |
| 0.0011 | 8.95 | 85 | 0.0005 |
| 0.0017 | 10.0 | 95 | 0.0014 |
| 0.0076 | 10.95 | 104 | 0.0004 |
| 0.0018 | 12.0 | 114 | 0.0003 |
| 0.0027 | 12.95 | 123 | 0.0003 |
| 0.0008 | 14.0 | 133 | 0.0003 |
| 0.0008 | 14.21 | 135 | 0.0003 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2