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: 28.3572
- Accuracy: 0.0169
- Dt Accuracy: 0.0169
- Df Accuracy: 0.0155
- 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: 0.0002
- 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 | 1.1452 | 0.7605 | 0.3886 | 0.3886 | None |
| No log | 2.0 | 64 | 2.5287 | 0.5105 | 0 | 0 | None |
| No log | 3.0 | 96 | 4.5225 | 0.3385 | 0 | 0 | None |
| No log | 4.0 | 128 | 8.2379 | 0.1565 | 0 | 0 | None |
| No log | 5.0 | 160 | 10.6257 | 0.0795 | 0 | 0 | None |
| No log | 6.0 | 192 | 10.2698 | 0.0335 | 0 | 0 | None |
| No log | 7.0 | 224 | 16.6444 | 0.022 | 0 | 0 | None |
| No log | 8.0 | 256 | 14.5998 | 0.0185 | 0 | 0 | None |
| No log | 9.0 | 288 | 20.3140 | 0.016 | 0 | 0 | None |
| No log | 10.0 | 320 | 20.2272 | 0.017 | 0 | 0 | None |
| No log | 11.0 | 352 | 21.0561 | 0.0165 | 0 | 0 | None |
| No log | 12.0 | 384 | 24.7484 | 0.016 | 0 | 0 | None |
| No log | 13.0 | 416 | 22.1982 | 0.0155 | 0 | 0 | None |
| No log | 14.0 | 448 | 26.3799 | 0.0155 | 0 | 0 | None |
| No log | 15.0 | 480 | 24.8184 | 0.0175 | 0 | 0 | None |
| 0.0 | 16.0 | 512 | 25.7616 | 0.0145 | 0 | 0 | None |
| 0.0 | 17.0 | 544 | 28.9583 | 0.0165 | 0 | 0 | None |
| 0.0 | 18.0 | 576 | 25.3188 | 0.0155 | 0 | 0 | None |
| 0.0 | 19.0 | 608 | 26.2113 | 0.016 | 0 | 0 | None |
| 0.0 | 20.0 | 640 | 28.3572 | 0.0155 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2