42
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: -7.5901
- Accuracy: 0.1781
- Dt Accuracy: 0.1781
- Df Accuracy: 0.175
- 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: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 16 | -0.5943 | 0.8955 | 0.2053 | 0.2053 | None |
| No log | 2.0 | 32 | -0.6878 | 0.851 | 0.2729 | 0.2729 | None |
| No log | 3.0 | 48 | -0.8240 | 0.8135 | 0.3244 | 0.3244 | None |
| No log | 4.0 | 64 | -1.0586 | 0.7495 | 0.4021 | 0.4021 | None |
| No log | 5.0 | 80 | -1.3593 | 0.686 | 0.4653 | 0.4653 | None |
| No log | 6.0 | 96 | -1.7478 | 0.6355 | 0.5028 | 0.5028 | None |
| No log | 7.0 | 112 | -2.3184 | 0.5545 | 0.5506 | 0.5506 | None |
| No log | 8.0 | 128 | -2.8628 | 0.489 | 0 | 0 | None |
| No log | 9.0 | 144 | -3.5199 | 0.4245 | 0 | 0 | None |
| No log | 10.0 | 160 | -4.2017 | 0.3815 | 0 | 0 | None |
| No log | 11.0 | 176 | -4.8407 | 0.3315 | 0 | 0 | None |
| No log | 12.0 | 192 | -5.3785 | 0.2875 | 0 | 0 | None |
| No log | 13.0 | 208 | -5.8581 | 0.258 | 0 | 0 | None |
| No log | 14.0 | 224 | -6.4548 | 0.235 | 0 | 0 | None |
| No log | 15.0 | 240 | -6.7097 | 0.2175 | 0 | 0 | None |
| No log | 16.0 | 256 | -6.9746 | 0.1955 | 0 | 0 | None |
| No log | 17.0 | 272 | -7.1407 | 0.1885 | 0 | 0 | None |
| No log | 18.0 | 288 | -7.4623 | 0.182 | 0 | 0 | None |
| No log | 19.0 | 304 | -7.4725 | 0.1775 | 0 | 0 | None |
| No log | 20.0 | 320 | -7.5901 | 0.175 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2