21
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: -4.1063
- Accuracy: 0.4392
- Dt Accuracy: 0.4392
- Df Accuracy: 0.4325
- 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: 21
- 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 | -0.6136 | 0.8725 | 0.2413 | 0.2413 | None |
| No log | 2.0 | 32 | -0.8276 | 0.7925 | 0.3529 | 0.3529 | None |
| No log | 3.0 | 48 | -1.2405 | 0.7215 | 0.4338 | 0.4338 | None |
| No log | 4.0 | 64 | -1.7847 | 0.646 | 0.5023 | 0.5023 | None |
| No log | 5.0 | 80 | -2.3938 | 0.574 | 0.5506 | 0.5506 | None |
| No log | 6.0 | 96 | -2.9835 | 0.518 | 0.5761 | 0.5761 | None |
| -2.3785 | 7.0 | 112 | -3.5109 | 0.4805 | 0 | 0 | None |
| -2.3785 | 8.0 | 128 | -3.9013 | 0.4495 | 0 | 0 | None |
| -2.3785 | 9.0 | 144 | -4.0748 | 0.4345 | 0 | 0 | None |
| -2.3785 | 10.0 | 160 | -4.1063 | 0.4325 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2