resnet-18-mnist-87
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: 0.0383
- Accuracy: 0.9882
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: 87
- 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 |
---|---|---|---|---|
0.7817 | 1.0 | 1594 | 0.0888 | 0.9769 |
0.4316 | 2.0 | 3188 | 0.0732 | 0.9799 |
0.4051 | 3.0 | 4782 | 0.0517 | 0.985 |
0.3755 | 4.0 | 6376 | 0.0511 | 0.9849 |
0.361 | 5.0 | 7970 | 0.0471 | 0.9868 |
0.3478 | 6.0 | 9564 | 0.0481 | 0.987 |
0.3346 | 7.0 | 11158 | 0.0449 | 0.9871 |
0.3294 | 8.0 | 12752 | 0.0433 | 0.9872 |
0.3235 | 9.0 | 14346 | 0.0383 | 0.9882 |
0.322 | 10.0 | 15940 | 0.0391 | 0.9881 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 2