resnet-50-cifar10-21
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2261
- Accuracy: 0.9276
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 |
---|---|---|---|---|
2.1038 | 1.0 | 1329 | 1.1908 | 0.6801 |
1.4232 | 2.0 | 2658 | 0.5594 | 0.8427 |
1.0584 | 3.0 | 3987 | 0.3672 | 0.8888 |
0.8348 | 4.0 | 5316 | 0.3042 | 0.908 |
0.7852 | 5.0 | 6645 | 0.2752 | 0.9124 |
0.7555 | 6.0 | 7974 | 0.2475 | 0.9197 |
0.7159 | 7.0 | 9303 | 0.2369 | 0.9249 |
0.7065 | 8.0 | 10632 | 0.2345 | 0.9247 |
0.6949 | 9.0 | 11961 | 0.2318 | 0.9256 |
0.6794 | 10.0 | 13290 | 0.2261 | 0.9276 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.18.0
- Tokenizers 0.13.3
- Downloads last month
- 20