100
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: 2.6575
- Accuracy: 0.4954
- Dt Accuracy: 0.4954
- Df Accuracy: 0.506
- 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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 100
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 16 | 0.7069 | 0.885 | 0.2214 | 0.2214 | None |
| No log | 2.0 | 32 | 0.9081 | 0.828 | 0.3043 | 0.3043 | None |
| No log | 3.0 | 48 | 1.2329 | 0.752 | 0.3979 | 0.3979 | None |
| No log | 4.0 | 64 | 1.4688 | 0.703 | 0 | 0 | None |
| No log | 5.0 | 80 | 1.8379 | 0.632 | 0 | 0 | None |
| No log | 6.0 | 96 | 2.1920 | 0.587 | 0 | 0 | None |
| 0.0 | 7.0 | 112 | 2.1717 | 0.568 | 0 | 0 | None |
| 0.0 | 8.0 | 128 | 2.3624 | 0.542 | 0 | 0 | None |
| 0.0 | 9.0 | 144 | 2.5881 | 0.513 | 0 | 0 | None |
| 0.0 | 10.0 | 160 | 2.6575 | 0.506 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2