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: -15.6211
- Accuracy: 0.053
- Dt Accuracy: 0.053
- Df Accuracy: 0.0527
- 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 | 24 | -0.5959 | 0.887 | 0.2188 | 0.2188 | None |
| No log | 2.0 | 48 | -0.7410 | 0.836 | 0.2942 | 0.2942 | None |
| No log | 3.0 | 72 | -1.0470 | 0.7677 | 0.3808 | 0.3808 | None |
| No log | 4.0 | 96 | -1.6607 | 0.6627 | 0.4852 | 0.4852 | None |
| No log | 5.0 | 120 | -2.8226 | 0.5427 | 0.5589 | 0.5589 | None |
| No log | 6.0 | 144 | -4.5649 | 0.4277 | 0 | 0 | None |
| No log | 7.0 | 168 | -6.6639 | 0.3173 | 0 | 0 | None |
| No log | 8.0 | 192 | -8.3560 | 0.234 | 0 | 0 | None |
| No log | 9.0 | 216 | -10.0509 | 0.173 | 0 | 0 | None |
| No log | 10.0 | 240 | -11.1596 | 0.1397 | 0 | 0 | None |
| No log | 11.0 | 264 | -12.2591 | 0.1107 | 0 | 0 | None |
| No log | 12.0 | 288 | -12.8758 | 0.0897 | 0 | 0 | None |
| No log | 13.0 | 312 | -13.7717 | 0.0807 | 0 | 0 | None |
| No log | 14.0 | 336 | -14.1966 | 0.0723 | 0 | 0 | None |
| No log | 15.0 | 360 | -14.8155 | 0.062 | 0 | 0 | None |
| No log | 16.0 | 384 | -14.2187 | 0.0563 | 0 | 0 | None |
| No log | 17.0 | 408 | -15.1638 | 0.0553 | 0 | 0 | None |
| No log | 18.0 | 432 | -15.2822 | 0.0533 | 0 | 0 | None |
| No log | 19.0 | 456 | -15.1900 | 0.053 | 0 | 0 | None |
| No log | 20.0 | 480 | -15.6211 | 0.0527 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2