87
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6095
- Accuracy: 0.8319
- Dt Accuracy: 0.8319
- Df Accuracy: 0.7422
- Unlearn Overall Accuracy: 0.4223
- 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: 87
- 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 |
|---|---|---|---|---|---|---|---|
| 1.5336 | 1.0 | 391 | 0.6245 | 0.7515 | 0.4102 | 0.4102 | None |
| 1.4451 | 2.0 | 782 | 0.6100 | 0.7422 | 0.4221 | 0.4221 | None |
| 1.383 | 3.0 | 1173 | 0.6158 | 0.7348 | 0.4312 | 0.4312 | None |
| 1.3108 | 4.0 | 1564 | 0.6181 | 0.7402 | 0.4243 | 0.4243 | None |
| 1.3015 | 5.0 | 1955 | 0.6163 | 0.735 | 0.4311 | 0.4311 | None |
| 1.2655 | 6.0 | 2346 | 0.6125 | 0.7392 | 0.4258 | 0.4258 | None |
| 1.2247 | 7.0 | 2737 | 0.6125 | 0.7355 | 0.4304 | 0.4304 | None |
| 1.1982 | 8.0 | 3128 | 0.6088 | 0.738 | 0.4275 | 0.4275 | None |
| 1.2349 | 9.0 | 3519 | 0.6087 | 0.7415 | 0.4233 | 0.4233 | None |
| 1.2011 | 10.0 | 3910 | 0.6095 | 0.7422 | 0.4223 | 0.4223 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0