food101-resnet50
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: 2.6809
- Accuracy: 0.4450
- F1: 0.4139
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 4.4966 | 1.0 | 1066 | 4.4586 | 0.1663 | 0.1547 |
| 3.814 | 2.0 | 2132 | 3.7423 | 0.2986 | 0.2620 |
| 3.2572 | 3.0 | 3198 | 3.1916 | 0.3625 | 0.3304 |
| 2.9359 | 4.0 | 4264 | 2.9002 | 0.3971 | 0.3687 |
| 2.8476 | 5.0 | 5330 | 2.8185 | 0.4083 | 0.3802 |
Framework versions
- Transformers 4.57.0
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1