2025-02-05-21-58-41-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: 0.0762
- Precision: 0.9810
- Recall: 0.9805
- F1: 0.9804
- Accuracy: 0.9766
- Top1 Accuracy: 0.9805
- Error Rate: 0.0234
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 |
|---|---|---|---|---|---|---|---|---|---|
| 2.4636 | 1.0 | 103 | 2.1548 | 0.6867 | 0.6293 | 0.5929 | 0.5824 | 0.6293 | 0.4176 |
| 1.3967 | 2.0 | 206 | 0.5586 | 0.8893 | 0.8780 | 0.8770 | 0.8743 | 0.8780 | 0.1257 |
| 0.4328 | 3.0 | 309 | 0.2100 | 0.9565 | 0.9512 | 0.9518 | 0.9524 | 0.9512 | 0.0476 |
| 0.2544 | 4.0 | 412 | 0.1414 | 0.9628 | 0.9610 | 0.9613 | 0.9588 | 0.9610 | 0.0412 |
| 0.171 | 5.0 | 515 | 0.1127 | 0.9690 | 0.9683 | 0.9683 | 0.9638 | 0.9683 | 0.0362 |
| 0.1556 | 6.0 | 618 | 0.0976 | 0.9715 | 0.9707 | 0.9706 | 0.9681 | 0.9707 | 0.0319 |
| 0.118 | 7.0 | 721 | 0.0762 | 0.9810 | 0.9805 | 0.9804 | 0.9766 | 0.9805 | 0.0234 |
| 0.1142 | 8.0 | 824 | 0.0853 | 0.9809 | 0.9805 | 0.9804 | 0.9813 | 0.9805 | 0.0187 |
| 0.0978 | 9.0 | 927 | 0.0798 | 0.9808 | 0.9805 | 0.9803 | 0.9788 | 0.9805 | 0.0212 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.20.3