resnet-18-mnist-13
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: 0.0357
- Accuracy: 0.9891
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 |
---|---|---|---|---|
0.7953 | 1.0 | 1594 | 0.0941 | 0.9757 |
0.4364 | 2.0 | 3188 | 0.0620 | 0.9841 |
0.3979 | 3.0 | 4782 | 0.0554 | 0.9834 |
0.3741 | 4.0 | 6376 | 0.0487 | 0.985 |
0.3684 | 5.0 | 7970 | 0.0429 | 0.9869 |
0.3503 | 6.0 | 9564 | 0.0394 | 0.988 |
0.3361 | 7.0 | 11158 | 0.0369 | 0.989 |
0.3355 | 8.0 | 12752 | 0.0373 | 0.9878 |
0.3298 | 9.0 | 14346 | 0.0357 | 0.9891 |
0.3224 | 10.0 | 15940 | 0.0354 | 0.9887 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 3