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: 0.5920
- Accuracy: 0.8331
- Dt Accuracy: 0.8331
- Df Accuracy: 0.8947
- Unlearn Overall Accuracy: 0.2068
- 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 |
|---|---|---|---|---|---|---|---|
| 1.4069 | 1.0 | 391 | 0.6127 | 0.886 | 0.2204 | 0.2204 | None |
| 1.3414 | 2.0 | 782 | 0.5950 | 0.8927 | 0.2099 | 0.2099 | None |
| 1.286 | 3.0 | 1173 | 0.5970 | 0.8897 | 0.2147 | 0.2147 | None |
| 1.2222 | 4.0 | 1564 | 0.5958 | 0.8907 | 0.2131 | 0.2131 | None |
| 1.1948 | 5.0 | 1955 | 0.5936 | 0.8893 | 0.2153 | 0.2153 | None |
| 1.1614 | 6.0 | 2346 | 0.5902 | 0.8927 | 0.2100 | 0.2100 | None |
| 1.1417 | 7.0 | 2737 | 0.5892 | 0.8923 | 0.2105 | 0.2105 | None |
| 1.0797 | 8.0 | 3128 | 0.5895 | 0.8947 | 0.2068 | 0.2068 | None |
| 1.107 | 9.0 | 3519 | 0.5906 | 0.8957 | 0.2052 | 0.2052 | None |
| 1.1081 | 10.0 | 3910 | 0.5920 | 0.8947 | 0.2068 | 0.2068 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0