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: 2.4447
- Accuracy: 0.5099
- Dt Accuracy: 0.5099
- Df Accuracy: 0.5215
- 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 32 | 0.6820 | 0.875 | 0.2370 | 0.2370 | None |
| No log | 2.0 | 64 | 0.8778 | 0.8195 | 0.3162 | 0.3162 | None |
| No log | 3.0 | 96 | 1.0700 | 0.7755 | 0.3709 | 0.3709 | None |
| 0.0 | 4.0 | 128 | 1.3721 | 0.7125 | 0.4392 | 0.4392 | None |
| 0.0 | 5.0 | 160 | 1.6344 | 0.6605 | 0 | 0 | None |
| 0.0 | 6.0 | 192 | 1.9531 | 0.5985 | 0 | 0 | None |
| 0.0 | 7.0 | 224 | 2.1613 | 0.569 | 0 | 0 | None |
| 0.0 | 8.0 | 256 | 2.2816 | 0.5405 | 0 | 0 | None |
| 0.0 | 9.0 | 288 | 2.4842 | 0.52 | 0 | 0 | None |
| 0.0 | 10.0 | 320 | 2.4447 | 0.5215 | 0 | 0 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0