efficientnet-b3-finetuned-food101
This model is a fine-tuned version of google/efficientnet-b3 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5278
- Accuracy: 0.9
- F1: 0.9042
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: 2e-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 | F1 |
|---|---|---|---|---|---|
| 4.1358 | 1.0 | 157 | 3.9867 | 0.328 | 0.3446 |
| 2.5658 | 2.0 | 314 | 2.4812 | 0.71 | 0.7205 |
| 1.5019 | 3.0 | 471 | 1.4903 | 0.806 | 0.8127 |
| 1.1238 | 4.0 | 628 | 0.9173 | 0.834 | 0.8377 |
| 1.0664 | 5.0 | 785 | 0.6943 | 0.8793 | 0.8803 |
| 0.8955 | 6.0 | 942 | 0.6340 | 0.8847 | 0.8874 |
| 0.8461 | 7.0 | 1099 | 0.5398 | 0.8907 | 0.8934 |
| 0.841 | 8.0 | 1256 | 0.5054 | 0.88 | 0.8863 |
| 0.8 | 9.0 | 1413 | 0.5278 | 0.9 | 0.9042 |
| 0.7614 | 9.9408 | 1560 | 0.5160 | 0.896 | 0.9002 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1