resnet-50-mnist-42
This model is a fine-tuned version of microsoft/resnet-50 on the mnist dataset. It achieves the following results on the evaluation set:
- Loss: 0.0867
- Accuracy: 0.9756
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: 42
- 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 |
---|---|---|---|---|
2.1104 | 1.0 | 1594 | 0.7291 | 0.844 |
0.7721 | 2.0 | 3188 | 0.2278 | 0.9488 |
0.648 | 3.0 | 4782 | 0.1525 | 0.9628 |
0.5634 | 4.0 | 6376 | 0.1187 | 0.9684 |
0.5422 | 5.0 | 7970 | 0.1046 | 0.9707 |
0.5031 | 6.0 | 9564 | 0.0981 | 0.9746 |
0.4926 | 7.0 | 11158 | 0.0909 | 0.975 |
0.4874 | 8.0 | 12752 | 0.0884 | 0.9751 |
0.4723 | 9.0 | 14346 | 0.0867 | 0.9756 |
0.4628 | 10.0 | 15940 | 0.0868 | 0.9753 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 2