13
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: -5.0649
- Accuracy: 0.3545
- Dt Accuracy: 0.3545
- Df Accuracy: 0.331
- 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: 13
- 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 | -0.6693 | 0.8525 | 0.2710 | 0.2710 | None |
| No log | 2.0 | 32 | -0.9524 | 0.778 | 0.3700 | 0.3700 | None |
| No log | 3.0 | 48 | -1.5007 | 0.6945 | 0.4583 | 0.4583 | None |
| No log | 4.0 | 64 | -2.2576 | 0.5875 | 0.5418 | 0.5418 | None |
| No log | 5.0 | 80 | -3.0301 | 0.5235 | 0.5687 | 0.5687 | None |
| No log | 6.0 | 96 | -3.7687 | 0.4535 | 0 | 0 | None |
| -2.773 | 7.0 | 112 | -4.4644 | 0.3955 | 0 | 0 | None |
| -2.773 | 8.0 | 128 | -4.8001 | 0.363 | 0 | 0 | None |
| -2.773 | 9.0 | 144 | -5.0436 | 0.3435 | 0 | 0 | None |
| -2.773 | 10.0 | 160 | -5.0649 | 0.331 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2