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: -6.7934
- Accuracy: 0.2407
- Dt Accuracy: 0.2407
- Df Accuracy: 0.233
- 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: 87
- 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 | -0.5914 | 0.892 | 0.2108 | 0.2108 | None |
| No log | 2.0 | 32 | -0.6586 | 0.8615 | 0.2575 | 0.2575 | None |
| No log | 3.0 | 48 | -0.7769 | 0.821 | 0.3146 | 0.3146 | None |
| No log | 4.0 | 64 | -0.9230 | 0.7855 | 0.3599 | 0.3599 | None |
| No log | 5.0 | 80 | -1.1711 | 0.728 | 0.4247 | 0.4247 | None |
| No log | 6.0 | 96 | -1.5399 | 0.6625 | 0.4851 | 0.4851 | None |
| No log | 7.0 | 112 | -2.0051 | 0.5945 | 0.5335 | 0.5335 | None |
| No log | 8.0 | 128 | -2.4841 | 0.5375 | 0.5623 | 0.5623 | None |
| No log | 9.0 | 144 | -3.0427 | 0.4785 | 0 | 0 | None |
| No log | 10.0 | 160 | -3.6661 | 0.4235 | 0 | 0 | None |
| No log | 11.0 | 176 | -4.3184 | 0.3825 | 0 | 0 | None |
| No log | 12.0 | 192 | -4.8470 | 0.3495 | 0 | 0 | None |
| No log | 13.0 | 208 | -5.4088 | 0.3195 | 0 | 0 | None |
| No log | 14.0 | 224 | -5.6832 | 0.2975 | 0 | 0 | None |
| No log | 15.0 | 240 | -6.1657 | 0.2695 | 0 | 0 | None |
| No log | 16.0 | 256 | -6.4715 | 0.251 | 0 | 0 | None |
| No log | 17.0 | 272 | -6.5817 | 0.2405 | 0 | 0 | None |
| No log | 18.0 | 288 | -6.6684 | 0.2325 | 0 | 0 | None |
| No log | 19.0 | 304 | -6.8003 | 0.231 | 0 | 0 | None |
| No log | 20.0 | 320 | -6.7934 | 0.233 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2