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: -17.1654
- Accuracy: 0.0357
- Dt Accuracy: 0.0357
- Df Accuracy: 0.0383
- 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 | 24 | -0.5887 | 0.886 | 0.2204 | 0.2204 | None |
| No log | 2.0 | 48 | -0.7637 | 0.828 | 0.3053 | 0.3053 | None |
| No log | 3.0 | 72 | -1.0760 | 0.756 | 0.3954 | 0.3954 | None |
| No log | 4.0 | 96 | -1.7602 | 0.6717 | 0.4778 | 0.4778 | None |
| No log | 5.0 | 120 | -3.0039 | 0.559 | 0.5535 | 0.5535 | None |
| No log | 6.0 | 144 | -4.8453 | 0.4383 | 0 | 0 | None |
| No log | 7.0 | 168 | -7.4014 | 0.317 | 0 | 0 | None |
| No log | 8.0 | 192 | -9.3582 | 0.2303 | 0 | 0 | None |
| No log | 9.0 | 216 | -10.3258 | 0.1617 | 0 | 0 | None |
| No log | 10.0 | 240 | -11.3833 | 0.1157 | 0 | 0 | None |
| No log | 11.0 | 264 | -12.7102 | 0.0847 | 0 | 0 | None |
| No log | 12.0 | 288 | -14.9483 | 0.071 | 0 | 0 | None |
| No log | 13.0 | 312 | -14.4654 | 0.0573 | 0 | 0 | None |
| No log | 14.0 | 336 | -15.6906 | 0.0497 | 0 | 0 | None |
| No log | 15.0 | 360 | -16.4326 | 0.046 | 0 | 0 | None |
| No log | 16.0 | 384 | -16.4055 | 0.0417 | 0 | 0 | None |
| No log | 17.0 | 408 | -17.2821 | 0.04 | 0 | 0 | None |
| No log | 18.0 | 432 | -17.7395 | 0.0393 | 0 | 0 | None |
| No log | 19.0 | 456 | -17.9212 | 0.0393 | 0 | 0 | None |
| No log | 20.0 | 480 | -17.1654 | 0.0383 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2