results
This model is a fine-tuned version of microsoft/resnet-18 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0032
- Accuracy: 0.9997
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4431 | 1.0 | 1744 | 0.2970 | 0.8746 |
| 0.3311 | 2.0 | 3488 | 0.1297 | 0.9613 |
| 0.1967 | 3.0 | 5232 | 0.0333 | 0.9945 |
| 0.0671 | 4.0 | 6976 | 0.0094 | 0.9987 |
| 0.1663 | 5.0 | 8720 | 0.0032 | 0.9997 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.19.1