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: -0.8361
- Accuracy: 0.7556
- Dt Accuracy: 0.7556
- Df Accuracy: 0.754
- Unlearn Overall Accuracy: 0.4008
- 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 | 8 | -0.5763 | 0.9 | 0.1981 | 0.1981 | None |
| No log | 2.0 | 16 | -0.5907 | 0.874 | 0.2392 | 0.2392 | None |
| No log | 3.0 | 24 | -0.6156 | 0.859 | 0.2618 | 0.2618 | None |
| No log | 4.0 | 32 | -0.6511 | 0.834 | 0.2981 | 0.2981 | None |
| No log | 5.0 | 40 | -0.6951 | 0.814 | 0.3255 | 0.3255 | None |
| No log | 6.0 | 48 | -0.7433 | 0.793 | 0.3532 | 0.3532 | None |
| No log | 7.0 | 56 | -0.7815 | 0.77 | 0.3821 | 0.3821 | None |
| No log | 8.0 | 64 | -0.8203 | 0.757 | 0.3975 | 0.3975 | None |
| No log | 9.0 | 72 | -0.8335 | 0.755 | 0.3997 | 0.3997 | None |
| No log | 10.0 | 80 | -0.8361 | 0.754 | 0.4008 | 0.4008 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2