resnet-34-mnist-100
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: 0.0270
- Accuracy: 0.9914
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 |
---|---|---|---|---|
0.738 | 1.0 | 1594 | 0.0834 | 0.9773 |
0.415 | 2.0 | 3188 | 0.0537 | 0.9837 |
0.3804 | 3.0 | 4782 | 0.0378 | 0.9888 |
0.3604 | 4.0 | 6376 | 0.0320 | 0.9891 |
0.3393 | 5.0 | 7970 | 0.0329 | 0.9899 |
0.3258 | 6.0 | 9564 | 0.0285 | 0.9908 |
0.3139 | 7.0 | 11158 | 0.0293 | 0.99 |
0.3075 | 8.0 | 12752 | 0.0270 | 0.9914 |
0.2846 | 9.0 | 14346 | 0.0250 | 0.9913 |
0.2967 | 10.0 | 15940 | 0.0257 | 0.9911 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 2