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: 0.1195
- Accuracy: 0.9681
- Dt Accuracy: 0.9681
- Df Accuracy: 0.967
- Unlearn Overall Accuracy: 0.2348
- 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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 21
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | 391 | 0.1371 | 0.978 | 0.2173 | 0.2173 | None |
| 0.4575 | 2.0 | 782 | 0.1261 | 0.979 | 0.2158 | 0.2158 | None |
| 0.4293 | 3.0 | 1173 | 0.1245 | 0.973 | 0.2253 | 0.2253 | None |
| 0.4095 | 4.0 | 1564 | 0.1225 | 0.975 | 0.2222 | 0.2222 | None |
| 0.4095 | 5.0 | 1955 | 0.1203 | 0.972 | 0.2269 | 0.2269 | None |
| 0.3879 | 6.0 | 2346 | 0.1248 | 0.968 | 0.2332 | 0.2332 | None |
| 0.3652 | 7.0 | 2737 | 0.1197 | 0.971 | 0.2285 | 0.2285 | None |
| 0.3617 | 8.0 | 3128 | 0.1200 | 0.967 | 0.2348 | 0.2348 | None |
| 0.347 | 9.0 | 3519 | 0.1194 | 0.964 | 0.2394 | 0.2394 | None |
| 0.347 | 10.0 | 3910 | 0.1195 | 0.967 | 0.2348 | 0.2348 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0