resnet50-finetune
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: 0.0122
- Accuracy: 0.9964
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
- 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
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1331 | 1.0 | 700 | 0.0665 | 0.9821 |
| 0.076 | 2.0 | 1400 | 0.0303 | 0.9889 |
| 0.0476 | 3.0 | 2100 | 0.0198 | 0.9925 |
| 0.0452 | 4.0 | 2800 | 0.0122 | 0.9964 |
| 0.0285 | 5.0 | 3500 | 0.0120 | 0.9957 |
| 0.0288 | 6.0 | 4200 | 0.0117 | 0.9954 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1