resnet-18-mnist-42
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: 0.0362
- Accuracy: 0.9904
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 |
---|---|---|---|---|
0.7731 | 1.0 | 1594 | 0.0818 | 0.981 |
0.426 | 2.0 | 3188 | 0.0602 | 0.9827 |
0.4048 | 3.0 | 4782 | 0.0528 | 0.9854 |
0.3694 | 4.0 | 6376 | 0.0475 | 0.9862 |
0.3677 | 5.0 | 7970 | 0.0423 | 0.9883 |
0.3426 | 6.0 | 9564 | 0.0413 | 0.9882 |
0.3411 | 7.0 | 11158 | 0.0389 | 0.99 |
0.3342 | 8.0 | 12752 | 0.0360 | 0.9901 |
0.325 | 9.0 | 14346 | 0.0361 | 0.9901 |
0.3147 | 10.0 | 15940 | 0.0362 | 0.9904 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 6