2025-01-21-14-35-49-resnet-50
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: 0.1215
- Precision: 0.9786
- Recall: 0.9778
- F1: 0.9778
- Accuracy: 0.9788
- Top1 Accuracy: 0.9778
- Error Rate: 0.0212
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: 0.0002
- train_batch_size: 32
- eval_batch_size: 32
- seed: 3407
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Top1 Accuracy | Error Rate |
|---|---|---|---|---|---|---|---|---|---|
| 1.5858 | 1.0 | 34 | 1.5129 | 0.6583 | 0.5407 | 0.5138 | 0.5418 | 0.5407 | 0.4582 |
| 1.3909 | 2.0 | 68 | 1.1807 | 0.7779 | 0.6519 | 0.6537 | 0.6522 | 0.6519 | 0.3478 |
| 1.059 | 3.0 | 102 | 0.7503 | 0.8897 | 0.8889 | 0.8867 | 0.8901 | 0.8889 | 0.1099 |
| 0.6942 | 4.0 | 136 | 0.4029 | 0.9427 | 0.9407 | 0.9402 | 0.9427 | 0.9407 | 0.0573 |
| 0.4241 | 5.0 | 170 | 0.2325 | 0.9673 | 0.9630 | 0.9624 | 0.9655 | 0.9630 | 0.0345 |
| 0.3235 | 6.0 | 204 | 0.1702 | 0.9673 | 0.9630 | 0.9630 | 0.9650 | 0.9630 | 0.0350 |
| 0.259 | 7.0 | 238 | 0.1359 | 0.9722 | 0.9704 | 0.9704 | 0.9719 | 0.9704 | 0.0281 |
| 0.2231 | 8.0 | 272 | 0.1225 | 0.9722 | 0.9704 | 0.9704 | 0.9719 | 0.9704 | 0.0281 |
| 0.2167 | 9.0 | 306 | 0.1253 | 0.9722 | 0.9704 | 0.9704 | 0.9719 | 0.9704 | 0.0281 |
| 0.1973 | 10.0 | 340 | 0.1215 | 0.9786 | 0.9778 | 0.9778 | 0.9788 | 0.9778 | 0.0212 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3