food-classification-ai-resnet-5e
This model is a fine-tuned version of microsoft/resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 498327.9375
- Accuracy: 0.4538
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 403987.475 | 1.0 | 947 | 498330.1875 | 0.2714 |
| 1050360.8 | 2.0 | 1894 | 498329.2188 | 0.3810 |
| 888766.6 | 3.0 | 2841 | 498328.5 | 0.4354 |
| 484782.35 | 4.0 | 3788 | 498327.9688 | 0.4470 |
| 565579.15 | 5.0 | 4735 | 498327.9375 | 0.4538 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1