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: -10.2412
- Accuracy: 0.0658
- Dt Accuracy: 0.0658
- Df Accuracy: 0.0645
- 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: 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 | 32 | -0.7541 | 0.8247 | 0.3101 | 0.3101 | None |
| No log | 2.0 | 64 | -1.6287 | 0.6282 | 0.5103 | 0.5103 | None |
| No log | 3.0 | 96 | -3.2728 | 0.4135 | 0 | 0 | None |
| -2.1706 | 4.0 | 128 | -5.0977 | 0.2622 | 0 | 0 | None |
| -2.1706 | 5.0 | 160 | -6.7898 | 0.157 | 0 | 0 | None |
| -2.1706 | 6.0 | 192 | -8.0704 | 0.1105 | 0 | 0 | None |
| -9.03 | 7.0 | 224 | -9.1750 | 0.0835 | 0 | 0 | None |
| -9.03 | 8.0 | 256 | -9.4854 | 0.0695 | 0 | 0 | None |
| -9.03 | 9.0 | 288 | -10.0105 | 0.0658 | 0 | 0 | None |
| -14.7769 | 10.0 | 320 | -10.2412 | 0.0645 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2