convnext-nano-5ep-batch-16
This model is a fine-tuned version of facebook/convnextv2-nano-22k-384 on the vuongnhathien/30VNFoods dataset. It achieves the following results on the evaluation set:
- Loss: 0.3835
- Accuracy: 0.9171
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.575 | 1.0 | 550 | 0.5743 | 0.8250 |
| 0.3134 | 2.0 | 1100 | 0.4706 | 0.8680 |
| 0.1174 | 3.0 | 1650 | 0.4487 | 0.8863 |
| 0.017 | 4.0 | 2200 | 0.3822 | 0.9129 |
| 0.0118 | 5.0 | 2750 | 0.3802 | 0.9137 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2