convnext-large-224-22k-1k-LongSleeveCleanedData
This model is a fine-tuned version of facebook/convnext-large-224-22k-1k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0060
- Accuracy: 0.9989
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 7
- total_train_batch_size: 56
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0805 | 0.99 | 143 | 0.0092 | 0.9978 |
| 0.0396 | 2.0 | 287 | 0.0060 | 0.9989 |
| 0.0382 | 3.0 | 431 | 0.0049 | 0.9989 |
| 0.0394 | 4.0 | 575 | 0.0035 | 0.9978 |
| 0.0269 | 5.0 | 719 | 0.0033 | 0.9989 |
| 0.0249 | 6.0 | 863 | 0.0035 | 0.9989 |
| 0.0388 | 7.0 | 1007 | 0.0058 | 0.9989 |
| 0.0175 | 7.99 | 1150 | 0.0039 | 0.9989 |
| 0.041 | 9.0 | 1294 | 0.0022 | 0.9989 |
| 0.0432 | 9.94 | 1430 | 0.0025 | 0.9989 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3