42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: -0.1102
- Accuracy: 0.9663
- Dt Accuracy: 0.9663
- Df Accuracy: 0.9845
- Unlearn Overall Accuracy: 0.2071
- 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: 1e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- 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 | -0.1089 | 0.9855 | 0.2055 | 0.2055 | None |
| No log | 2.0 | 32 | -0.1086 | 0.9855 | 0.2055 | 0.2055 | None |
| No log | 3.0 | 48 | -0.1082 | 0.985 | 0.2063 | 0.2063 | None |
| No log | 4.0 | 64 | -0.1090 | 0.9845 | 0.2071 | 0.2071 | None |
| No log | 5.0 | 80 | -0.1089 | 0.984 | 0.2079 | 0.2079 | None |
| No log | 6.0 | 96 | -0.1094 | 0.984 | 0.2079 | 0.2079 | None |
| No log | 7.0 | 112 | -0.1105 | 0.984 | 0.2079 | 0.2079 | None |
| No log | 8.0 | 128 | -0.1099 | 0.9835 | 0.2086 | 0.2086 | None |
| No log | 9.0 | 144 | -0.1112 | 0.9845 | 0.2070 | 0.2070 | None |
| No log | 10.0 | 160 | -0.1102 | 0.9845 | 0.2071 | 0.2071 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2