| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/efficientnet-b3 |
| tags: |
| - generated_from_trainer |
| model-index: |
| - name: results_final |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information the Trainer had access to. You |
| should probably proofread and complete it, then remove this comment. --> |
|
|
| # results_final |
| |
| This model is a fine-tuned version of [google/efficientnet-b3](https://huggingface.co/google/efficientnet-b3) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 5.4534 |
| |
| ## 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: 0.07 |
| - train_batch_size: 16 |
| - eval_batch_size: 16 |
| - seed: 42 |
| - 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_steps: 0.02 |
| - num_epochs: 30 |
| - mixed_precision_training: Native AMP |
|
|
| ### Training results |
|
|
| | Training Loss | Epoch | Step | Validation Loss | |
| |:-------------:|:-----:|:----:|:---------------:| |
| | 3.7801 | 1.0 | 240 | 3.5997 | |
| | 3.6030 | 2.0 | 480 | 3.4122 | |
| | 3.5533 | 3.0 | 720 | 3.4880 | |
| | 3.4716 | 4.0 | 960 | 3.5813 | |
| | 3.3849 | 5.0 | 1200 | 3.8072 | |
| | 3.3499 | 6.0 | 1440 | 3.1296 | |
| | 3.2501 | 7.0 | 1680 | 3.3787 | |
| | 3.2307 | 8.0 | 1920 | 3.2702 | |
| | 3.1690 | 9.0 | 2160 | 3.4604 | |
| | 3.1316 | 10.0 | 2400 | 3.0390 | |
| | 3.1056 | 11.0 | 2640 | 3.6019 | |
| | 3.0999 | 12.0 | 2880 | 3.3648 | |
| | 3.0658 | 13.0 | 3120 | 3.2586 | |
| | 3.0190 | 14.0 | 3360 | 3.3761 | |
| | 2.9633 | 15.0 | 3600 | 3.4629 | |
| | 2.9125 | 16.0 | 3840 | 2.9820 | |
| | 2.8926 | 17.0 | 4080 | 2.9411 | |
| | 2.8830 | 18.0 | 4320 | 2.8852 | |
| | 2.8468 | 19.0 | 4560 | 2.8470 | |
| | 2.8401 | 20.0 | 4800 | 3.1739 | |
| | 2.8407 | 21.0 | 5040 | 2.8360 | |
| | 2.8088 | 22.0 | 5280 | 2.8013 | |
| | 2.7835 | 23.0 | 5520 | 2.7773 | |
| | 2.7627 | 24.0 | 5760 | 2.7736 | |
| | 2.7417 | 25.0 | 6000 | 2.8376 | |
| | 2.7228 | 26.0 | 6240 | 2.7436 | |
| | 2.7087 | 27.0 | 6480 | 2.7369 | |
| | 2.6784 | 28.0 | 6720 | 2.7986 | |
| | 2.6436 | 29.0 | 6960 | 2.7207 | |
| | 2.6153 | 30.0 | 7200 | 5.4534 | |
|
|
|
|
| ### Framework versions |
|
|
| - Transformers 5.13.1 |
| - Pytorch 2.11.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
|
|
