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: -26.2433
- Accuracy: 0.0307
- Dt Accuracy: 0.0307
- Df Accuracy: 0.0315
- 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 | 32 | -0.6938 | 0.8595 | 0.2603 | 0.2603 | None |
| No log | 2.0 | 64 | -1.0389 | 0.7662 | 0.3823 | 0.3823 | None |
| No log | 3.0 | 96 | -1.8701 | 0.6175 | 0.5156 | 0.5156 | None |
| No log | 4.0 | 128 | -3.4103 | 0.4515 | 0 | 0 | None |
| No log | 5.0 | 160 | -5.7976 | 0.297 | 0 | 0 | None |
| No log | 6.0 | 192 | -8.2683 | 0.1885 | 0 | 0 | None |
| No log | 7.0 | 224 | -9.9573 | 0.1328 | 0 | 0 | None |
| No log | 8.0 | 256 | -12.9612 | 0.088 | 0 | 0 | None |
| No log | 9.0 | 288 | -14.8736 | 0.0673 | 0 | 0 | None |
| No log | 10.0 | 320 | -16.5217 | 0.0558 | 0 | 0 | None |
| No log | 11.0 | 352 | -18.2991 | 0.049 | 0 | 0 | None |
| No log | 12.0 | 384 | -20.0140 | 0.045 | 0 | 0 | None |
| No log | 13.0 | 416 | -21.9695 | 0.0415 | 0 | 0 | None |
| No log | 14.0 | 448 | -23.1051 | 0.0375 | 0 | 0 | None |
| No log | 15.0 | 480 | -24.3409 | 0.036 | 0 | 0 | None |
| -16.5851 | 16.0 | 512 | -26.2172 | 0.0333 | 0 | 0 | None |
| -16.5851 | 17.0 | 544 | -26.5100 | 0.0325 | 0 | 0 | None |
| -16.5851 | 18.0 | 576 | -26.4346 | 0.0325 | 0 | 0 | None |
| -16.5851 | 19.0 | 608 | -25.1473 | 0.032 | 0 | 0 | None |
| -16.5851 | 20.0 | 640 | -26.2433 | 0.0315 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2