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: -8.0172
- Accuracy: 0.1805
- Dt Accuracy: 0.1805
- Df Accuracy: 0.1885
- Unlearn Overall Accuracy: 0
- Unlearn Time: None
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: 5e-05
- train_batch_size: 128
- 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 | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 32 | -0.1529 | 0.9728 | 0.2254 | 0.2254 | None |
| No log | 2.0 | 64 | -0.6452 | 0.8645 | 0.3722 | 0.3722 | None |
| No log | 3.0 | 96 | -2.1054 | 0.6645 | 0.5349 | 0.5349 | None |
| No log | 4.0 | 128 | -3.8360 | 0.5122 | 0 | 0 | None |
| No log | 5.0 | 160 | -5.0851 | 0.418 | 0 | 0 | None |
| No log | 6.0 | 192 | -6.0913 | 0.3315 | 0 | 0 | None |
| No log | 7.0 | 224 | -7.0367 | 0.2585 | 0 | 0 | None |
| No log | 8.0 | 256 | -7.6828 | 0.2142 | 0 | 0 | None |
| No log | 9.0 | 288 | -8.0302 | 0.1945 | 0 | 0 | None |
| No log | 10.0 | 320 | -8.0172 | 0.1885 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2