efficientnet-b0-finetuned-noh
This model is a fine-tuned version of google/efficientnet-b0 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3784
- Accuracy: 0.8883
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: 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 |
|---|---|---|---|---|
| 0.6146 | 1.0 | 23 | 0.6139 | 0.7291 |
| 0.5116 | 2.0 | 46 | 0.4704 | 0.8309 |
| 0.4655 | 3.0 | 69 | 0.4233 | 0.8588 |
| 0.4331 | 4.0 | 92 | 0.4119 | 0.8604 |
| 0.4281 | 5.0 | 115 | 0.3897 | 0.8752 |
| 0.4001 | 6.0 | 138 | 0.4012 | 0.8719 |
| 0.3721 | 7.0 | 161 | 0.3861 | 0.8818 |
| 0.3979 | 8.0 | 184 | 0.3784 | 0.8883 |
| 0.3376 | 9.0 | 207 | 0.4171 | 0.8604 |
| 0.3984 | 9.5778 | 220 | 0.4139 | 0.8621 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1
- Datasets 2.19.1
- Tokenizers 0.21.0