resnet-50-finetuned-kidney_v4
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.2780
- Accuracy: 0.8999
- F1: 0.8982
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 5.1324 | 1.0 | 734 | 1.2224 | 0.6253 | 0.6188 |
| 3.4505 | 2.0 | 1468 | 0.5319 | 0.7929 | 0.7848 |
| 2.7887 | 3.0 | 2202 | 0.4337 | 0.8229 | 0.8150 |
| 2.9235 | 4.0 | 2936 | 0.3507 | 0.8747 | 0.8715 |
| 2.3171 | 5.0 | 3670 | 0.3191 | 0.8917 | 0.8895 |
| 2.0718 | 6.0 | 4404 | 0.2944 | 0.8958 | 0.8945 |
| 2.1077 | 7.0 | 5138 | 0.2900 | 0.8903 | 0.8881 |
| 2.1443 | 8.0 | 5872 | 0.2769 | 0.8978 | 0.8964 |
| 2.1161 | 9.0 | 6606 | 0.2780 | 0.8999 | 0.8982 |
| 2.3355 | 10.0 | 7340 | 0.2809 | 0.8965 | 0.8950 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2