resnet-50-mnist-13
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: 0.0791
- Accuracy: 0.9764
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: 13
- 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 |
---|---|---|---|---|
2.1198 | 1.0 | 1594 | 0.8804 | 0.7823 |
0.8593 | 2.0 | 3188 | 0.2470 | 0.9478 |
0.6696 | 3.0 | 4782 | 0.1468 | 0.9599 |
0.5621 | 4.0 | 6376 | 0.1149 | 0.9688 |
0.5491 | 5.0 | 7970 | 0.1024 | 0.9702 |
0.5092 | 6.0 | 9564 | 0.0928 | 0.9734 |
0.4892 | 7.0 | 11158 | 0.0861 | 0.9743 |
0.479 | 8.0 | 12752 | 0.0873 | 0.9731 |
0.4798 | 9.0 | 14346 | 0.0840 | 0.9746 |
0.4666 | 10.0 | 15940 | 0.0791 | 0.9764 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 14