resnet-18-mnist-100
This model is a fine-tuned version of microsoft/resnet-18 on the mnist dataset. It achieves the following results on the evaluation set:
- Loss: 0.0324
- Accuracy: 0.9901
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: 2e-05
- train_batch_size: 32
- eval_batch_size: 256
- seed: 100
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.7676 | 1.0 | 1594 | 0.1127 | 0.9694 |
0.4374 | 2.0 | 3188 | 0.0698 | 0.9799 |
0.406 | 3.0 | 4782 | 0.0463 | 0.9853 |
0.3821 | 4.0 | 6376 | 0.0454 | 0.987 |
0.357 | 5.0 | 7970 | 0.0406 | 0.9863 |
0.3489 | 6.0 | 9564 | 0.0352 | 0.9887 |
0.3357 | 7.0 | 11158 | 0.0354 | 0.9893 |
0.3325 | 8.0 | 12752 | 0.0348 | 0.9886 |
0.3094 | 9.0 | 14346 | 0.0318 | 0.9899 |
0.319 | 10.0 | 15940 | 0.0324 | 0.9901 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 17