resnet-34-mnist-21
This model is a fine-tuned version of microsoft/resnet-34 on the mnist dataset. It achieves the following results on the evaluation set:
- Loss: 0.0273
- Accuracy: 0.9918
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: 21
- 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 |
---|---|---|---|---|
0.7345 | 1.0 | 1594 | 0.0721 | 0.9788 |
0.4164 | 2.0 | 3188 | 0.0452 | 0.987 |
0.388 | 3.0 | 4782 | 0.0453 | 0.9866 |
0.3529 | 4.0 | 6376 | 0.0352 | 0.9897 |
0.3398 | 5.0 | 7970 | 0.0366 | 0.9883 |
0.3199 | 6.0 | 9564 | 0.0354 | 0.9891 |
0.3154 | 7.0 | 11158 | 0.0332 | 0.99 |
0.3025 | 8.0 | 12752 | 0.0273 | 0.9918 |
0.3029 | 9.0 | 14346 | 0.0274 | 0.9916 |
0.294 | 10.0 | 15940 | 0.0264 | 0.9918 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 2